Not in the top 1,000 by GitHub stars
OpenLAIR/OpenSkill
Open-World Self-Evolution for LLM Agents — agents that build both their skills and their own verification signals from scratch, with no target-task supervision. (Code coming soon.)
History
Review weekly changes to SKILL.md before updating. Dates mark the weeks in which we observed each version; checks apply to the recorded commits.
View weekly changes
tasks-evolved/3d-scan-calc/environment/skills/evo-3d-scan-calc/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Local scripts → After Local scripts
84ca182da055 → 84ca182da055
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → 84ca182da055
No earlier version was observed for comparison.
tasks-evolved/3d-scan-calc/environment/skills/evo-mass-report-output/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Local scripts → After Local scripts
84ca182da055 → 84ca182da055
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → 84ca182da055
No earlier version was observed for comparison.
tasks-evolved/3d-scan-calc/environment/skills/evo-mesh-geometry-analysis/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Local scripts → After Local scripts
84ca182da055 → 84ca182da055
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → 84ca182da055
No earlier version was observed for comparison.
tasks-evolved/3d-scan-calc/environment/skills/evo-stl-binary-parser/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Local scripts → After Local scripts
84ca182da055 → 84ca182da055
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → 84ca182da055
No earlier version was observed for comparison.
tasks-evolved/adaptive-cruise-control/environment/skills/evo-adaptive-cruise-control/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Local scripts → After Local scripts
84ca182da055 → 84ca182da055
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → 84ca182da055
No earlier version was observed for comparison.
tasks-evolved/azure-bgp-oscillation-route-leak/environment/skills/evo-azure-bgp-oscillation-route-leak/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Local scripts → After Local scripts
84ca182da055 → 84ca182da055
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → 84ca182da055
No earlier version was observed for comparison.
tasks-evolved/citation-check/environment/skills/evo-bibtex-parser/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Local scripts → After Local scripts
84ca182da055 → 84ca182da055
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → 84ca182da055
No earlier version was observed for comparison.
tasks-evolved/citation-check/environment/skills/evo-citation-scorer/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Local scripts → After Local scripts
84ca182da055 → 84ca182da055
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → 84ca182da055
No earlier version was observed for comparison.
tasks-evolved/citation-check/environment/skills/evo-citation-verifier/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
84ca182da055 → 84ca182da055
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 84ca182da055
No earlier version was observed for comparison.
tasks-evolved/civ6-adjacency-optimizer/environment/skills/evo-civ6-adjacency-rules/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Local scripts → After Local scripts
84ca182da055 → 84ca182da055
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → 84ca182da055
No earlier version was observed for comparison.
tasks-evolved/civ6-adjacency-optimizer/environment/skills/evo-civ6-map-parser/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Local scripts → After Local scripts
84ca182da055 → 84ca182da055
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → 84ca182da055
No earlier version was observed for comparison.
tasks-evolved/civ6-adjacency-optimizer/environment/skills/evo-civ6-placement-optimizer/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Local scripts → After Local scripts
84ca182da055 → 84ca182da055
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → 84ca182da055
No earlier version was observed for comparison.
tasks-evolved/court-form-filling/environment/skills/evo-pdf-field-inspector/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Local scripts → After Local scripts
84ca182da055 → 84ca182da055
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → 84ca182da055
No earlier version was observed for comparison.
tasks-evolved/court-form-filling/environment/skills/evo-pdf-form-filler/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Local scripts → After Local scripts
84ca182da055 → 84ca182da055
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → 84ca182da055
No earlier version was observed for comparison.
tasks-evolved/crystallographic-wyckoff-position-analysis/environment/skills/evo-crystallography-fraction-format/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Local scripts → After Local scripts
84ca182da055 → 84ca182da055
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → 84ca182da055
No earlier version was observed for comparison.
tasks-evolved/crystallographic-wyckoff-position-analysis/environment/skills/evo-crystallography-wyckoff-analysis/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Local scripts → After Local scripts
84ca182da055 → 84ca182da055
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → 84ca182da055
No earlier version was observed for comparison.
tasks-evolved/dapt-intrusion-detection/environment/skills/evo-network-stats-computation/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Local scripts → After Local scripts
84ca182da055 → 84ca182da055
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → 84ca182da055
No earlier version was observed for comparison.
tasks-evolved/dapt-intrusion-detection/environment/skills/evo-pcap-feature-extraction/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Local scripts → After Local scripts
84ca182da055 → 84ca182da055
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → 84ca182da055
No earlier version was observed for comparison.
tasks-evolved/data-to-d3/environment/skills/evo-d3v6-stock-visualization/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Local scripts → After Local scripts
84ca182da055 → 84ca182da055
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → 84ca182da055
No earlier version was observed for comparison.
tasks-evolved/data-to-d3/environment/skills/evo-web-scaffold-generator/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
84ca182da055 → 84ca182da055
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 84ca182da055
No earlier version was observed for comparison.
tasks-evolved/dialogue-parser/environment/skills/evo-dialogue-dotgen/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Local scripts → After Local scripts
84ca182da055 → 84ca182da055
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → 84ca182da055
No earlier version was observed for comparison.
tasks-evolved/dialogue-parser/environment/skills/evo-dialogue-output/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Local scripts → After Local scripts
84ca182da055 → 84ca182da055
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → 84ca182da055
No earlier version was observed for comparison.
tasks-evolved/dialogue-parser/environment/skills/evo-dialogue-parser/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Local scripts → After Local scripts
84ca182da055 → 84ca182da055
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → 84ca182da055
No earlier version was observed for comparison.
tasks-evolved/dynamic-object-aware-egomotion/environment/skills/evo-egomotion-dynamic-analysis/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Local scripts → After Local scripts
84ca182da055 → 84ca182da055
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → 84ca182da055
No earlier version was observed for comparison.
tasks-evolved/dynamic-object-aware-egomotion/environment/skills/evo-output-serialization/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Local scripts → After Local scripts
84ca182da055 → 84ca182da055
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → 84ca182da055
No earlier version was observed for comparison.
tasks-evolved/dynamic-object-aware-egomotion/environment/skills/evo-video-sampling/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Local scripts → After Local scripts
84ca182da055 → 84ca182da055
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → 84ca182da055
No earlier version was observed for comparison.
tasks-evolved/earthquake-phase-association/environment/skills/evo-seismic-data-io/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Local scripts → After Local scripts
84ca182da055 → 84ca182da055
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → 84ca182da055
No earlier version was observed for comparison.
tasks-evolved/earthquake-phase-association/environment/skills/evo-seismic-phase-association/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Local scripts → After Local scripts
84ca182da055 → 84ca182da055
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → 84ca182da055
No earlier version was observed for comparison.
tasks-evolved/earthquake-phase-association/environment/skills/evo-seismic-phase-picking/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Local scripts → After Local scripts
84ca182da055 → 84ca182da055
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → 84ca182da055
No earlier version was observed for comparison.
tasks-evolved/earthquake-plate-calculation/environment/skills/evo-geospatial-antimeridian-plates/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Local scripts → After Local scripts
84ca182da055 → 84ca182da055
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → 84ca182da055
No earlier version was observed for comparison.
tasks-evolved/earthquake-plate-calculation/environment/skills/evo-geospatial-earthquake-distance/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Local scripts → After Local scripts
84ca182da055 → 84ca182da055
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → 84ca182da055
No earlier version was observed for comparison.
tasks-evolved/econ-detrending-correlation/environment/skills/evo-macro-cycle-correlation/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Local scripts → After Local scripts
84ca182da055 → 84ca182da055
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → 84ca182da055
No earlier version was observed for comparison.
tasks-evolved/econ-detrending-correlation/environment/skills/evo-macro-data-ingestion/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Local scripts → After Local scripts
84ca182da055 → 84ca182da055
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → 84ca182da055
No earlier version was observed for comparison.
tasks-evolved/energy-ac-optimal-power-flow/environment/skills/evo-acopf-network-parser/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Local scripts → After Local scripts
84ca182da055 → 84ca182da055
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → 84ca182da055
No earlier version was observed for comparison.
tasks-evolved/energy-ac-optimal-power-flow/environment/skills/evo-acopf-report-generator/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Local scripts → After Local scripts
84ca182da055 → 84ca182da055
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → 84ca182da055
No earlier version was observed for comparison.
tasks-evolved/energy-ac-optimal-power-flow/environment/skills/evo-acopf-solver/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Local scripts → After Local scripts
84ca182da055 → 84ca182da055
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → 84ca182da055
No earlier version was observed for comparison.
tasks-evolved/energy-market-pricing/environment/skills/evo-dcopf-solver/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Local scripts → After Local scripts
84ca182da055 → 84ca182da055
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → 84ca182da055
No earlier version was observed for comparison.
tasks-evolved/energy-market-pricing/environment/skills/evo-market-report/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Local scripts → After Local scripts
84ca182da055 → 84ca182da055
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → 84ca182da055
No earlier version was observed for comparison.
tasks-evolved/energy-market-pricing/environment/skills/evo-matpower-parser/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Local scripts → After Local scripts
84ca182da055 → 84ca182da055
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → 84ca182da055
No earlier version was observed for comparison.
tasks-evolved/enterprise-information-search/environment/skills/evo-enterprise-doc-parser/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Local scripts → After Local scripts
84ca182da055 → 84ca182da055
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → 84ca182da055
No earlier version was observed for comparison.
tasks-evolved/enterprise-information-search/environment/skills/evo-enterprise-qa-pipeline/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Local scripts → After Local scripts
84ca182da055 → 84ca182da055
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → 84ca182da055
No earlier version was observed for comparison.
tasks-evolved/exceltable-in-ppt/environment/skills/evo-pptx-embedded-excel-updater/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Local scripts → After Local scripts
84ca182da055 → 84ca182da055
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → 84ca182da055
No earlier version was observed for comparison.
tasks-evolved/exoplanet-detection-period/environment/skills/evo-tess-lightcurve-preprocessing/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Local scripts → After Local scripts
84ca182da055 → 84ca182da055
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → 84ca182da055
No earlier version was observed for comparison.
tasks-evolved/exoplanet-detection-period/environment/skills/evo-transit-period-detection/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Local scripts → After Local scripts
84ca182da055 → 84ca182da055
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → 84ca182da055
No earlier version was observed for comparison.
tasks-evolved/financial-modeling-qa/environment/skills/evo-excel-match-analyzer/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Local scripts → After Local scripts
84ca182da055 → 84ca182da055
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → 84ca182da055
No earlier version was observed for comparison.
tasks-evolved/financial-modeling-qa/environment/skills/evo-pdf-context-extractor/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Local scripts → After Local scripts
84ca182da055 → 84ca182da055
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → 84ca182da055
No earlier version was observed for comparison.
tasks-evolved/find-topk-similiar-chemicals/environment/skills/evo-molecule-similarity/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Local scripts → After Local scripts
84ca182da055 → 84ca182da055
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → 84ca182da055
No earlier version was observed for comparison.
tasks-evolved/fix-build-agentops/environment/skills/evo-build-diagnosis/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Local scripts → After Local scripts
84ca182da055 → 84ca182da055
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → 84ca182da055
No earlier version was observed for comparison.
tasks-evolved/fix-build-agentops/environment/skills/evo-patch-generate-apply/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Local scripts → After Local scripts
84ca182da055 → 84ca182da055
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → 84ca182da055
No earlier version was observed for comparison.
tasks-evolved/fix-build-agentops/environment/skills/evo-python-build-fixer/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Local scripts → After Local scripts
84ca182da055 → 84ca182da055
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → 84ca182da055
No earlier version was observed for comparison.
tasks-evolved/fix-build-google-auto/environment/skills/evo-maven-build-diagnosis/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Local scripts → After Local scripts
84ca182da055 → 84ca182da055
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → 84ca182da055
No earlier version was observed for comparison.
tasks-evolved/fix-build-google-auto/environment/skills/evo-maven-patch-generation/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Local scripts → After Local scripts
84ca182da055 → 84ca182da055
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → 84ca182da055
No earlier version was observed for comparison.
tasks-evolved/fix-druid-loophole-cve/environment/skills/evo-druid-cve-patch/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Local scripts → After Local scripts
84ca182da055 → 84ca182da055
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → 84ca182da055
No earlier version was observed for comparison.
tasks-evolved/fix-erlang-ssh-cve/environment/skills/evo-erlang-ssh-cve-patch/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Local scripts → After Local scripts
84ca182da055 → 84ca182da055
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → 84ca182da055
No earlier version was observed for comparison.
tasks-evolved/flink-query/environment/skills/evo-flink-session-job/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Local scripts → After Local scripts
84ca182da055 → 84ca182da055
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → 84ca182da055
No earlier version was observed for comparison.
tasks-evolved/flood-risk-analysis/environment/skills/evo-flood-risk-analysis/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
84ca182da055 → 84ca182da055
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 84ca182da055
No earlier version was observed for comparison.
tasks-evolved/flood-risk-analysis/environment/skills/evo-usgs-flood-detection/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Local scripts → After Local scripts
84ca182da055 → 84ca182da055
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → 84ca182da055
No earlier version was observed for comparison.
tasks-evolved/gh-repo-analytics/environment/skills/evo-gh-data-fetcher/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
84ca182da055 → 84ca182da055
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 84ca182da055
No earlier version was observed for comparison.
tasks-evolved/gh-repo-analytics/environment/skills/evo-gh-report-generator/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Local scripts → After Local scripts
84ca182da055 → 84ca182da055
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → 84ca182da055
No earlier version was observed for comparison.
tasks-evolved/glm-lake-mendota/environment/skills/evo-glm-simulation/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
84ca182da055 → 84ca182da055
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 84ca182da055
No earlier version was observed for comparison.
tasks-evolved/gravitational-wave-detection/environment/skills/evo-gw-grid-search-output/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Local scripts → After Local scripts
84ca182da055 → 84ca182da055
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → 84ca182da055
No earlier version was observed for comparison.
tasks-evolved/gravitational-wave-detection/environment/skills/evo-gw-matched-filter-engine/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Local scripts → After Local scripts
84ca182da055 → 84ca182da055
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → 84ca182da055
No earlier version was observed for comparison.
tasks-evolved/grid-dispatch-operator/environment/skills/evo-grid-dispatch-operator/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Local scripts → After Local scripts
84ca182da055 → 84ca182da055
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → 84ca182da055
No earlier version was observed for comparison.
tasks-evolved/hvac-control/environment/skills/evo-thermal-pid-control/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Local scripts → After Local scripts
84ca182da055 → 84ca182da055
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → 84ca182da055
No earlier version was observed for comparison.
tasks-evolved/hvac-control/environment/skills/evo-thermal-sysid/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Local scripts → After Local scripts
84ca182da055 → 84ca182da055
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → 84ca182da055
No earlier version was observed for comparison.
tasks-evolved/invoice-fraud-detection/environment/skills/evo-invoice-fraud-detector/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Local scripts → After Local scripts
84ca182da055 → 84ca182da055
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → 84ca182da055
No earlier version was observed for comparison.
tasks-evolved/invoice-fraud-detection/environment/skills/evo-pdf-invoice-parser/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Local scripts → After Local scripts
84ca182da055 → 84ca182da055
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → 84ca182da055
No earlier version was observed for comparison.
tasks-evolved/invoice-fraud-detection/environment/skills/evo-reference-data-loader/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Local scripts → After Local scripts
84ca182da055 → 84ca182da055
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → 84ca182da055
No earlier version was observed for comparison.
tasks-evolved/jax-computing-basics/environment/skills/evo-jax-compute/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Local scripts → After Local scripts
84ca182da055 → 84ca182da055
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → 84ca182da055
No earlier version was observed for comparison.
tasks-evolved/jax-computing-basics/environment/skills/evo-jax-computing-basics/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Local scripts → After Local scripts
84ca182da055 → 84ca182da055
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → 84ca182da055
No earlier version was observed for comparison.
tasks-evolved/jax-computing-basics/environment/skills/evo-jax-io/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Local scripts → After Local scripts
84ca182da055 → 84ca182da055
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → 84ca182da055
No earlier version was observed for comparison.
tasks-evolved/jpg-ocr-stat/environment/skills/evo-ocr-preprocess-extract/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Local scripts → After Local scripts
84ca182da055 → 84ca182da055
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → 84ca182da055
No earlier version was observed for comparison.
tasks-evolved/jpg-ocr-stat/environment/skills/evo-receipt-parse-export/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Local scripts → After Local scripts
84ca182da055 → 84ca182da055
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → 84ca182da055
No earlier version was observed for comparison.
tasks-evolved/lab-unit-harmonization/environment/skills/evo-clinical-data-cleaning/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Local scripts → After Local scripts
84ca182da055 → 84ca182da055
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → 84ca182da055
No earlier version was observed for comparison.
tasks-evolved/lab-unit-harmonization/environment/skills/evo-clinical-unit-harmonization/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Local scripts → After Local scripts
84ca182da055 → 84ca182da055
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → 84ca182da055
No earlier version was observed for comparison.
tasks-evolved/lake-warming-attribution/environment/skills/evo-lake-data-pipeline/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Local scripts → After Local scripts
84ca182da055 → 84ca182da055
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → 84ca182da055
No earlier version was observed for comparison.
tasks-evolved/lake-warming-attribution/environment/skills/evo-lake-factor-attribution/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Local scripts → After Local scripts
84ca182da055 → 84ca182da055
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → 84ca182da055
No earlier version was observed for comparison.
tasks-evolved/lake-warming-attribution/environment/skills/evo-lake-trend-analysis/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Local scripts → After Local scripts
84ca182da055 → 84ca182da055
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → 84ca182da055
No earlier version was observed for comparison.
tasks-evolved/latex-formula-extraction/environment/skills/evo-latex-formula-extraction/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Local scripts → After Local scripts
84ca182da055 → 84ca182da055
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → 84ca182da055
No earlier version was observed for comparison.
tasks-evolved/latex-formula-extraction/environment/skills/evo-latex-syntax-validation/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Local scripts → After Local scripts
84ca182da055 → 84ca182da055
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → 84ca182da055
No earlier version was observed for comparison.
tasks-evolved/latex-formula-extraction/environment/skills/evo-pdf-to-markdown/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Local scripts → After Local scripts
84ca182da055 → 84ca182da055
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → 84ca182da055
No earlier version was observed for comparison.
tasks-evolved/lean4-proof/environment/skills/evo-lean4-recursive-sequence-inequality-proof/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Local scripts → After Local scripts
84ca182da055 → 84ca182da055
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → 84ca182da055
No earlier version was observed for comparison.
tasks-evolved/manufacturing-codebook-normalization/environment/skills/evo-defect-pipeline/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Local scripts → After Local scripts
84ca182da055 → 84ca182da055
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → 84ca182da055
No earlier version was observed for comparison.
tasks-evolved/manufacturing-codebook-normalization/environment/skills/evo-fuzzy-match/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Local scripts → After Local scripts
84ca182da055 → 84ca182da055
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → 84ca182da055
No earlier version was observed for comparison.
tasks-evolved/manufacturing-codebook-normalization/environment/skills/evo-text-normalize/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Local scripts → After Local scripts
84ca182da055 → 84ca182da055
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → 84ca182da055
No earlier version was observed for comparison.
tasks-evolved/manufacturing-equipment-maintenance/environment/skills/evo-reflow-handbook-parser/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Local scripts → After Local scripts
84ca182da055 → 84ca182da055
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → 84ca182da055
No earlier version was observed for comparison.
tasks-evolved/manufacturing-equipment-maintenance/environment/skills/evo-reflow-json-output/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Local scripts → After Local scripts
84ca182da055 → 84ca182da055
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → 84ca182da055
No earlier version was observed for comparison.
tasks-evolved/manufacturing-equipment-maintenance/environment/skills/evo-reflow-thermal-analysis/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Local scripts → After Local scripts
84ca182da055 → 84ca182da055
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → 84ca182da055
No earlier version was observed for comparison.
tasks-evolved/manufacturing-fjsp-optimization/environment/skills/evo-fjsp-data-io/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Local scripts → After Local scripts
84ca182da055 → 84ca182da055
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → 84ca182da055
No earlier version was observed for comparison.
tasks-evolved/manufacturing-fjsp-optimization/environment/skills/evo-fjsp-scheduler/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Local scripts → After Local scripts
84ca182da055 → 84ca182da055
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → 84ca182da055
No earlier version was observed for comparison.
tasks-evolved/manufacturing-fjsp-optimization/environment/skills/evo-fjsp-validator/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Local scripts → After Local scripts
84ca182da055 → 84ca182da055
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → 84ca182da055
No earlier version was observed for comparison.
tasks-evolved/mario-coin-counting/environment/skills/evo-template-matching-counter/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Local scripts → After Local scripts
84ca182da055 → 84ca182da055
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → 84ca182da055
No earlier version was observed for comparison.
tasks-evolved/mario-coin-counting/environment/skills/evo-video-keyframe-extraction/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Local scripts → After Local scripts
84ca182da055 → 84ca182da055
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → 84ca182da055
No earlier version was observed for comparison.
tasks-evolved/mars-clouds-clustering/environment/skills/evo-mars-clustering-eval/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Local scripts → After Local scripts
84ca182da055 → 84ca182da055
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → 84ca182da055
No earlier version was observed for comparison.
tasks-evolved/mars-clouds-clustering/environment/skills/evo-mars-grid-search/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Local scripts → After Local scripts
84ca182da055 → 84ca182da055
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → 84ca182da055
No earlier version was observed for comparison.
tasks-evolved/mars-clouds-clustering/environment/skills/evo-mars-pareto-output/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Local scripts → After Local scripts
84ca182da055 → 84ca182da055
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → 84ca182da055
No earlier version was observed for comparison.
tasks-evolved/multilingual-video-dubbing/environment/skills/evo-dubbing-audio-processing/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Local scripts → After Local scripts
84ca182da055 → 84ca182da055
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → 84ca182da055
No earlier version was observed for comparison.
tasks-evolved/multilingual-video-dubbing/environment/skills/evo-dubbing-mux-report/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Local scripts → After Local scripts
84ca182da055 → 84ca182da055
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → 84ca182da055
No earlier version was observed for comparison.
tasks-evolved/multilingual-video-dubbing/environment/skills/evo-dubbing-tts-synthesis/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Local scripts → After Local scripts
84ca182da055 → 84ca182da055
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → 84ca182da055
No earlier version was observed for comparison.
tasks-evolved/offer-letter-generator/environment/skills/evo-docx-template-filler/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Local scripts → After Local scripts
84ca182da055 → 84ca182da055
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → 84ca182da055
No earlier version was observed for comparison.
tasks-evolved/organize-messy-files/environment/skills/evo-document-classify-and-sort/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Local scripts → After Local scripts
84ca182da055 → 84ca182da055
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → 84ca182da055
No earlier version was observed for comparison.
tasks-evolved/organize-messy-files/environment/skills/evo-document-text-extraction/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Local scripts → After Local scripts
84ca182da055 → 84ca182da055
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → 84ca182da055
No earlier version was observed for comparison.
tasks-evolved/paper-anonymizer/environment/skills/evo-pdf-content-extraction/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Local scripts → After Local scripts
84ca182da055 → 84ca182da055
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → 84ca182da055
No earlier version was observed for comparison.
tasks-evolved/paper-anonymizer/environment/skills/evo-pdf-redaction-engine/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Local scripts → After Local scripts
84ca182da055 → 84ca182da055
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → 84ca182da055
No earlier version was observed for comparison.
tasks-evolved/parallel-tfidf-search/environment/skills/evo-parallel-batch-search/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Local scripts → After Local scripts
84ca182da055 → 84ca182da055
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → 84ca182da055
No earlier version was observed for comparison.
tasks-evolved/parallel-tfidf-search/environment/skills/evo-parallel-determinism/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Local scripts → After Local scripts
84ca182da055 → 84ca182da055
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → 84ca182da055
No earlier version was observed for comparison.
tasks-evolved/parallel-tfidf-search/environment/skills/evo-parallel-index-building/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Local scripts → After Local scripts
84ca182da055 → 84ca182da055
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → 84ca182da055
No earlier version was observed for comparison.
tasks-evolved/pddl-tpp-planning/environment/skills/evo-tpp-solver/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Local scripts → After Local scripts
84ca182da055 → 84ca182da055
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → 84ca182da055
No earlier version was observed for comparison.
tasks-evolved/pdf-excel-diff/environment/skills/evo-dataframe-diff-report/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Local scripts → After Local scripts
84ca182da055 → 84ca182da055
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → 84ca182da055
No earlier version was observed for comparison.
tasks-evolved/pdf-excel-diff/environment/skills/evo-pdf-excel-extraction/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Local scripts → After Local scripts
84ca182da055 → 84ca182da055
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → 84ca182da055
No earlier version was observed for comparison.
tasks-evolved/pedestrian-traffic-counting/environment/skills/evo-pedestrian-vlm-counting/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Local scripts → After Local scripts
84ca182da055 → 84ca182da055
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → 84ca182da055
No earlier version was observed for comparison.
tasks-evolved/pedestrian-traffic-counting/environment/skills/evo-video-frame-extraction/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Local scripts → After Local scripts
84ca182da055 → 84ca182da055
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → 84ca182da055
No earlier version was observed for comparison.
tasks-evolved/pg-essay-to-audiobook/environment/skills/evo-tts-audiobook-synth/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Local scripts → After Local scripts
84ca182da055 → 84ca182da055
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → 84ca182da055
No earlier version was observed for comparison.
tasks-evolved/pg-essay-to-audiobook/environment/skills/evo-web-essay-scraper/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
84ca182da055 → 84ca182da055
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 84ca182da055
No earlier version was observed for comparison.
tasks-evolved/powerlifting-coef-calc/environment/skills/evo-openpyxl-sheet-processor/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Local scripts → After Local scripts
84ca182da055 → 84ca182da055
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → 84ca182da055
No earlier version was observed for comparison.
tasks-evolved/powerlifting-coef-calc/environment/skills/evo-powerlifting-dots-formula/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Local scripts → After Local scripts
84ca182da055 → 84ca182da055
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → 84ca182da055
No earlier version was observed for comparison.
tasks-evolved/pptx-reference-formatting/environment/skills/evo-pptx-reference-slide/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Local scripts → After Local scripts
84ca182da055 → 84ca182da055
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → 84ca182da055
No earlier version was observed for comparison.
tasks-evolved/pptx-reference-formatting/environment/skills/evo-pptx-title-detect-format/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Local scripts → After Local scripts
84ca182da055 → 84ca182da055
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → 84ca182da055
No earlier version was observed for comparison.
tasks-evolved/pptx-reference-formatting/environment/skills/evo-pptx-xml-io/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Local scripts → After Local scripts
84ca182da055 → 84ca182da055
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → 84ca182da055
No earlier version was observed for comparison.
tasks-evolved/protein-expression-analysis/environment/skills/evo-protein-expression-analysis/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Local scripts → After Local scripts
84ca182da055 → 84ca182da055
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → 84ca182da055
No earlier version was observed for comparison.
tasks-evolved/protein-expression-analysis/environment/skills/evo-proteomics-excel-formulas/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Local scripts → After Local scripts
84ca182da055 → 84ca182da055
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → 84ca182da055
No earlier version was observed for comparison.
tasks-evolved/python-scala-translation/environment/skills/evo-scala-idiom-mapping/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Local scripts → After Local scripts
84ca182da055 → 84ca182da055
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → 84ca182da055
No earlier version was observed for comparison.
tasks-evolved/python-scala-translation/environment/skills/evo-scala-tokenizer-generator/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Local scripts → After Local scripts
84ca182da055 → 84ca182da055
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → 84ca182da055
No earlier version was observed for comparison.
tasks-evolved/quantum-numerical-simulation/environment/skills/evo-dicke-model-simulation/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Local scripts → After Local scripts
84ca182da055 → 84ca182da055
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → 84ca182da055
No earlier version was observed for comparison.
tasks-evolved/quantum-numerical-simulation/environment/skills/evo-wigner-csv-export/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Local scripts → After Local scripts
84ca182da055 → 84ca182da055
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → 84ca182da055
No earlier version was observed for comparison.
tasks-evolved/r2r-mpc-control/environment/skills/evo-r2r-linearization/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Local scripts → After Local scripts
84ca182da055 → 84ca182da055
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → 84ca182da055
No earlier version was observed for comparison.
tasks-evolved/r2r-mpc-control/environment/skills/evo-r2r-mpc-controller/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Local scripts → After Local scripts
84ca182da055 → 84ca182da055
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → 84ca182da055
No earlier version was observed for comparison.
tasks-evolved/react-performance-debugging/environment/skills/evo-nextjs-api-optimization/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Local scripts → After Local scripts
84ca182da055 → 84ca182da055
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → 84ca182da055
No earlier version was observed for comparison.
tasks-evolved/react-performance-debugging/environment/skills/evo-nextjs-bundle-reduction/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Local scripts → After Local scripts
84ca182da055 → 84ca182da055
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → 84ca182da055
No earlier version was observed for comparison.
tasks-evolved/react-performance-debugging/environment/skills/evo-nextjs-render-optimization/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Local scripts → After Local scripts
84ca182da055 → 84ca182da055
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → 84ca182da055
No earlier version was observed for comparison.
tasks-evolved/reserves-at-risk-calc/environment/skills/evo-excel-data-extraction/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Local scripts → After Local scripts
84ca182da055 → 84ca182da055
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → 84ca182da055
No earlier version was observed for comparison.
tasks-evolved/reserves-at-risk-calc/environment/skills/evo-excel-financial-formulas/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Local scripts → After Local scripts
84ca182da055 → 84ca182da055
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → 84ca182da055
No earlier version was observed for comparison.
tasks-evolved/sales-pivot-analysis/environment/skills/evo-sales-pivot-analysis/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Local scripts → After Local scripts
84ca182da055 → 84ca182da055
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → 84ca182da055
No earlier version was observed for comparison.
tasks-evolved/sec-financial-report/environment/skills/evo-sec13f-analyzer/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Local scripts → After Local scripts
84ca182da055 → 84ca182da055
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → 84ca182da055
No earlier version was observed for comparison.
tasks-evolved/seismic-phase-picking/environment/skills/evo-seismic-data-preprocessing/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Local scripts → After Local scripts
84ca182da055 → 84ca182da055
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → 84ca182da055
No earlier version was observed for comparison.
tasks-evolved/seismic-phase-picking/environment/skills/evo-seismic-phase-picking/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Local scripts → After Local scripts
84ca182da055 → 84ca182da055
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → 84ca182da055
No earlier version was observed for comparison.
tasks-evolved/setup-fuzzing-py/environment/skills/evo-atheris-fuzz-driver/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Local scripts → After Local scripts
84ca182da055 → 84ca182da055
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → 84ca182da055
No earlier version was observed for comparison.
tasks-evolved/setup-fuzzing-py/environment/skills/evo-fuzz-env-runner/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Local scripts → After Local scripts
84ca182da055 → 84ca182da055
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → 84ca182da055
No earlier version was observed for comparison.
tasks-evolved/setup-fuzzing-py/environment/skills/evo-python-library-discovery/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Local scripts → After Local scripts
84ca182da055 → 84ca182da055
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → 84ca182da055
No earlier version was observed for comparison.
tasks-evolved/shock-analysis-demand/environment/skills/evo-macro-demand-shock-scenarios/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Local scripts → After Local scripts
84ca182da055 → 84ca182da055
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → 84ca182da055
No earlier version was observed for comparison.
tasks-evolved/shock-analysis-demand/environment/skills/evo-macro-sut-import-share/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Local scripts → After Local scripts
84ca182da055 → 84ca182da055
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → 84ca182da055
No earlier version was observed for comparison.
tasks-evolved/shock-analysis-demand/environment/skills/evo-macro-weo-data/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Local scripts → After Local scripts
84ca182da055 → 84ca182da055
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → 84ca182da055
No earlier version was observed for comparison.
tasks-evolved/simpo-code-reproduction/environment/skills/evo-simpo-code-reproduction/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Local scripts → After Local scripts
84ca182da055 → 84ca182da055
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → 84ca182da055
No earlier version was observed for comparison.
tasks-evolved/software-dependency-audit/environment/skills/evo-software-dependency-audit/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Local scripts → After Local scripts
84ca182da055 → 84ca182da055
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → 84ca182da055
No earlier version was observed for comparison.
tasks-evolved/speaker-diarization-subtitles/environment/skills/evo-speaker-diarization-subtitles/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
84ca182da055 → 84ca182da055
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 84ca182da055
No earlier version was observed for comparison.
tasks-evolved/spring-boot-jakarta-migration/environment/skills/evo-spring-boot-jakarta-migration/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Local scripts → After Local scripts
84ca182da055 → 84ca182da055
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → 84ca182da055
No earlier version was observed for comparison.
tasks-evolved/suricata-custom-exfil/environment/skills/evo-suricata-custom-exfil/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Local scripts → After Local scripts
84ca182da055 → 84ca182da055
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → 84ca182da055
No earlier version was observed for comparison.
tasks-evolved/syzkaller-ppdev-syzlang/environment/skills/evo-syzkaller-ppdev-syzlang/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Local scripts → After Local scripts
84ca182da055 → 84ca182da055
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → 84ca182da055
No earlier version was observed for comparison.
tasks-evolved/taxonomy-tree-merge/environment/skills/evo-cluster-naming/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Local scripts → After Local scripts
84ca182da055 → 84ca182da055
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → 84ca182da055
No earlier version was observed for comparison.
tasks-evolved/taxonomy-tree-merge/environment/skills/evo-semantic-hierarchical-clustering/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Local scripts → After Local scripts
84ca182da055 → 84ca182da055
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → 84ca182da055
No earlier version was observed for comparison.
tasks-evolved/taxonomy-tree-merge/environment/skills/evo-taxonomy-data-pipeline/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Local scripts → After Local scripts
84ca182da055 → 84ca182da055
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → 84ca182da055
No earlier version was observed for comparison.
tasks-evolved/threejs-structure-parser/environment/skills/evo-threejs-scene-parser/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Local scripts → After Local scripts
84ca182da055 → 84ca182da055
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → 84ca182da055
No earlier version was observed for comparison.
tasks-evolved/threejs-to-obj/environment/skills/evo-threejs-obj-export/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Local scripts → After Local scripts
84ca182da055 → 84ca182da055
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → 84ca182da055
No earlier version was observed for comparison.
tasks-evolved/threejs-to-obj/environment/skills/evo-threejs-to-obj/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Local scripts → After Local scripts
84ca182da055 → 84ca182da055
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → 84ca182da055
No earlier version was observed for comparison.
tasks-evolved/travel-planning/environment/skills/evo-travel-data-search/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Local scripts → After Local scripts
84ca182da055 → 84ca182da055
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → 84ca182da055
No earlier version was observed for comparison.
tasks-evolved/travel-planning/environment/skills/evo-travel-itinerary-builder/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Local scripts → After Local scripts
84ca182da055 → 84ca182da055
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → 84ca182da055
No earlier version was observed for comparison.
tasks-evolved/travel-planning/environment/skills/evo-travel-planning/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Local scripts → After Local scripts
84ca182da055 → 84ca182da055
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → 84ca182da055
No earlier version was observed for comparison.
tasks-evolved/trend-anomaly-causal-inference/environment/skills/evo-trend-anomaly-causal-inference/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Local scripts → After Local scripts
84ca182da055 → 84ca182da055
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → 84ca182da055
No earlier version was observed for comparison.
tasks-evolved/video-filler-word-remover/environment/skills/evo-video-filler-word-remover/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Local scripts → After Local scripts
84ca182da055 → 84ca182da055
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → 84ca182da055
No earlier version was observed for comparison.
tasks-evolved/video-tutorial-indexer/environment/skills/evo-video-tutorial-indexer/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Local scripts → After Local scripts
84ca182da055 → 84ca182da055
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → 84ca182da055
No earlier version was observed for comparison.
tasks-evolved/virtualhome-agent-planning/environment/skills/evo-pddl-plan-formatter/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Local scripts → After Local scripts
84ca182da055 → 84ca182da055
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → 84ca182da055
No earlier version was observed for comparison.
tasks-evolved/virtualhome-agent-planning/environment/skills/evo-pddl-solver/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Local scripts → After Local scripts
84ca182da055 → 84ca182da055
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → 84ca182da055
No earlier version was observed for comparison.
tasks-evolved/virtualhome-agent-planning/environment/skills/evo-virtualhome-agent-planning/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Local scripts → After Local scripts
84ca182da055 → 84ca182da055
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → 84ca182da055
No earlier version was observed for comparison.
tasks-evolved/weighted-gdp-calc/environment/skills/evo-excel-gcc-net-exports-formulas/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Local scripts → After Local scripts
84ca182da055 → 84ca182da055
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → 84ca182da055
No earlier version was observed for comparison.
tasks-evolved/weighted-gdp-calc/environment/skills/evo-excel-workbook-formula-io/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
84ca182da055 → 84ca182da055
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 84ca182da055
No earlier version was observed for comparison.
tasks-evolved/xlsx-recover-data/environment/skills/evo-excel-io/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Local scripts → After Local scripts
84ca182da055 → 84ca182da055
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → 84ca182da055
No earlier version was observed for comparison.
tasks-evolved/xlsx-recover-data/environment/skills/evo-nasa-budget-recovery/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Local scripts → After Local scripts
84ca182da055 → 84ca182da055
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → 84ca182da055
No earlier version was observed for comparison.
tasks-evolved/xlsx-recover-data/environment/skills/evo-xlsx-recover-data/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
84ca182da055 → 84ca182da055
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 84ca182da055
No earlier version was observed for comparison.
Verified commit 84ca182da055fafb6453dcec4a6defdbbfd987c1
git clone --filter=blob:none --no-checkout https://github.com/OpenLAIR/OpenSkill.git .hotskills/openlair-openskill && git -C .hotskills/openlair-openskill checkout --detach 84ca182da055fafb6453dcec4a6defdbbfd987c1
# Copy each selected skill directory from .hotskills/openlair-openskill into .claude/skills/<skill-name>/Heat
0.3- Star growth, last 7 daysNot available
- Star growth, last 24 hoursNot available
- Rank movement, last 7 daysNot available
- Commits, last 30 daysNot available
- Accounts asking about it through MCP, last 7 daysNot available
- Hot votes this weekNot available
Heat never changes the order by stars, and sponsorship never touches it. How heat works
Stars over time
30-day change not yet available: not enough history.
Individual skills in this repository
- evo-3d-scan-calc
tasks-evolved/3d-scan-calc/environment/skills/evo-3d-scan-calc - evo-mass-report-output
tasks-evolved/3d-scan-calc/environment/skills/evo-mass-report-output - evo-mesh-geometry-analysis
tasks-evolved/3d-scan-calc/environment/skills/evo-mesh-geometry-analysis - evo-stl-binary-parser
tasks-evolved/3d-scan-calc/environment/skills/evo-stl-binary-parser - evo-adaptive-cruise-control
tasks-evolved/adaptive-cruise-control/environment/skills/evo-adaptive-cruise-control - evo-azure-bgp-oscillation-route-leak
tasks-evolved/azure-bgp-oscillation-route-leak/environment/skills/evo-azure-bgp-oscillation-route-leak - evo-bibtex-parser
tasks-evolved/citation-check/environment/skills/evo-bibtex-parser - evo-citation-scorer
tasks-evolved/citation-check/environment/skills/evo-citation-scorer - evo-citation-verifier
tasks-evolved/citation-check/environment/skills/evo-citation-verifier - evo-civ6-adjacency-rules
tasks-evolved/civ6-adjacency-optimizer/environment/skills/evo-civ6-adjacency-rules - evo-civ6-map-parser
tasks-evolved/civ6-adjacency-optimizer/environment/skills/evo-civ6-map-parser - evo-civ6-placement-optimizer
tasks-evolved/civ6-adjacency-optimizer/environment/skills/evo-civ6-placement-optimizer - evo-pdf-field-inspector
tasks-evolved/court-form-filling/environment/skills/evo-pdf-field-inspector - evo-pdf-form-filler
tasks-evolved/court-form-filling/environment/skills/evo-pdf-form-filler - evo-crystallography-fraction-format
tasks-evolved/crystallographic-wyckoff-position-analysis/environment/skills/evo-crystallography-fraction-format - evo-crystallography-wyckoff-analysis
tasks-evolved/crystallographic-wyckoff-position-analysis/environment/skills/evo-crystallography-wyckoff-analysis - evo-network-stats-computation
tasks-evolved/dapt-intrusion-detection/environment/skills/evo-network-stats-computation - evo-pcap-feature-extraction
tasks-evolved/dapt-intrusion-detection/environment/skills/evo-pcap-feature-extraction - evo-d3v6-stock-visualization
tasks-evolved/data-to-d3/environment/skills/evo-d3v6-stock-visualization - evo-web-scaffold-generator
tasks-evolved/data-to-d3/environment/skills/evo-web-scaffold-generator - evo-dialogue-dotgen
tasks-evolved/dialogue-parser/environment/skills/evo-dialogue-dotgen - evo-dialogue-output
tasks-evolved/dialogue-parser/environment/skills/evo-dialogue-output - evo-dialogue-parser
tasks-evolved/dialogue-parser/environment/skills/evo-dialogue-parser - evo-egomotion-dynamic-analysis
tasks-evolved/dynamic-object-aware-egomotion/environment/skills/evo-egomotion-dynamic-analysis - evo-output-serialization
tasks-evolved/dynamic-object-aware-egomotion/environment/skills/evo-output-serialization - evo-video-sampling
tasks-evolved/dynamic-object-aware-egomotion/environment/skills/evo-video-sampling - evo-seismic-data-io
tasks-evolved/earthquake-phase-association/environment/skills/evo-seismic-data-io - evo-seismic-phase-association
tasks-evolved/earthquake-phase-association/environment/skills/evo-seismic-phase-association - evo-seismic-phase-picking
tasks-evolved/earthquake-phase-association/environment/skills/evo-seismic-phase-picking - evo-geospatial-antimeridian-plates
tasks-evolved/earthquake-plate-calculation/environment/skills/evo-geospatial-antimeridian-plates - evo-geospatial-earthquake-distance
tasks-evolved/earthquake-plate-calculation/environment/skills/evo-geospatial-earthquake-distance - evo-macro-cycle-correlation
tasks-evolved/econ-detrending-correlation/environment/skills/evo-macro-cycle-correlation - evo-macro-data-ingestion
tasks-evolved/econ-detrending-correlation/environment/skills/evo-macro-data-ingestion - evo-acopf-network-parser
tasks-evolved/energy-ac-optimal-power-flow/environment/skills/evo-acopf-network-parser - evo-acopf-report-generator
tasks-evolved/energy-ac-optimal-power-flow/environment/skills/evo-acopf-report-generator - evo-acopf-solver
tasks-evolved/energy-ac-optimal-power-flow/environment/skills/evo-acopf-solver - evo-dcopf-solver
tasks-evolved/energy-market-pricing/environment/skills/evo-dcopf-solver - evo-market-report
tasks-evolved/energy-market-pricing/environment/skills/evo-market-report - evo-matpower-parser
tasks-evolved/energy-market-pricing/environment/skills/evo-matpower-parser - evo-enterprise-doc-parser
tasks-evolved/enterprise-information-search/environment/skills/evo-enterprise-doc-parser - evo-enterprise-qa-pipeline
tasks-evolved/enterprise-information-search/environment/skills/evo-enterprise-qa-pipeline - evo-pptx-embedded-excel-updater
tasks-evolved/exceltable-in-ppt/environment/skills/evo-pptx-embedded-excel-updater - evo-tess-lightcurve-preprocessing
tasks-evolved/exoplanet-detection-period/environment/skills/evo-tess-lightcurve-preprocessing - evo-transit-period-detection
tasks-evolved/exoplanet-detection-period/environment/skills/evo-transit-period-detection - evo-excel-match-analyzer
tasks-evolved/financial-modeling-qa/environment/skills/evo-excel-match-analyzer - evo-pdf-context-extractor
tasks-evolved/financial-modeling-qa/environment/skills/evo-pdf-context-extractor - evo-molecule-similarity
tasks-evolved/find-topk-similiar-chemicals/environment/skills/evo-molecule-similarity - evo-build-diagnosis
tasks-evolved/fix-build-agentops/environment/skills/evo-build-diagnosis - evo-patch-generate-apply
tasks-evolved/fix-build-agentops/environment/skills/evo-patch-generate-apply - evo-python-build-fixer
tasks-evolved/fix-build-agentops/environment/skills/evo-python-build-fixer - evo-maven-build-diagnosis
tasks-evolved/fix-build-google-auto/environment/skills/evo-maven-build-diagnosis - evo-maven-patch-generation
tasks-evolved/fix-build-google-auto/environment/skills/evo-maven-patch-generation - evo-druid-cve-patch
tasks-evolved/fix-druid-loophole-cve/environment/skills/evo-druid-cve-patch - evo-erlang-ssh-cve-patch
tasks-evolved/fix-erlang-ssh-cve/environment/skills/evo-erlang-ssh-cve-patch - evo-flink-session-job
tasks-evolved/flink-query/environment/skills/evo-flink-session-job - evo-flood-risk-analysis
tasks-evolved/flood-risk-analysis/environment/skills/evo-flood-risk-analysis - evo-usgs-flood-detection
tasks-evolved/flood-risk-analysis/environment/skills/evo-usgs-flood-detection - evo-gh-data-fetcher
tasks-evolved/gh-repo-analytics/environment/skills/evo-gh-data-fetcher - evo-gh-report-generator
tasks-evolved/gh-repo-analytics/environment/skills/evo-gh-report-generator - evo-glm-simulation
tasks-evolved/glm-lake-mendota/environment/skills/evo-glm-simulation - evo-gw-grid-search-output
tasks-evolved/gravitational-wave-detection/environment/skills/evo-gw-grid-search-output - evo-gw-matched-filter-engine
tasks-evolved/gravitational-wave-detection/environment/skills/evo-gw-matched-filter-engine - evo-grid-dispatch-operator
tasks-evolved/grid-dispatch-operator/environment/skills/evo-grid-dispatch-operator - evo-thermal-pid-control
tasks-evolved/hvac-control/environment/skills/evo-thermal-pid-control - evo-thermal-sysid
tasks-evolved/hvac-control/environment/skills/evo-thermal-sysid - evo-invoice-fraud-detector
tasks-evolved/invoice-fraud-detection/environment/skills/evo-invoice-fraud-detector - evo-pdf-invoice-parser
tasks-evolved/invoice-fraud-detection/environment/skills/evo-pdf-invoice-parser - evo-reference-data-loader
tasks-evolved/invoice-fraud-detection/environment/skills/evo-reference-data-loader - evo-jax-compute
tasks-evolved/jax-computing-basics/environment/skills/evo-jax-compute - evo-jax-computing-basics
tasks-evolved/jax-computing-basics/environment/skills/evo-jax-computing-basics - evo-jax-io
tasks-evolved/jax-computing-basics/environment/skills/evo-jax-io - evo-ocr-preprocess-extract
tasks-evolved/jpg-ocr-stat/environment/skills/evo-ocr-preprocess-extract - evo-receipt-parse-export
tasks-evolved/jpg-ocr-stat/environment/skills/evo-receipt-parse-export - evo-clinical-data-cleaning
tasks-evolved/lab-unit-harmonization/environment/skills/evo-clinical-data-cleaning - evo-clinical-unit-harmonization
tasks-evolved/lab-unit-harmonization/environment/skills/evo-clinical-unit-harmonization - evo-lake-data-pipeline
tasks-evolved/lake-warming-attribution/environment/skills/evo-lake-data-pipeline - evo-lake-factor-attribution
tasks-evolved/lake-warming-attribution/environment/skills/evo-lake-factor-attribution - evo-lake-trend-analysis
tasks-evolved/lake-warming-attribution/environment/skills/evo-lake-trend-analysis - evo-latex-formula-extraction
tasks-evolved/latex-formula-extraction/environment/skills/evo-latex-formula-extraction - evo-latex-syntax-validation
tasks-evolved/latex-formula-extraction/environment/skills/evo-latex-syntax-validation - evo-pdf-to-markdown
tasks-evolved/latex-formula-extraction/environment/skills/evo-pdf-to-markdown - evo-lean4-recursive-sequence-inequality-proof
tasks-evolved/lean4-proof/environment/skills/evo-lean4-recursive-sequence-inequality-proof - evo-defect-pipeline
tasks-evolved/manufacturing-codebook-normalization/environment/skills/evo-defect-pipeline - evo-fuzzy-match
tasks-evolved/manufacturing-codebook-normalization/environment/skills/evo-fuzzy-match - evo-text-normalize
tasks-evolved/manufacturing-codebook-normalization/environment/skills/evo-text-normalize - evo-reflow-handbook-parser
tasks-evolved/manufacturing-equipment-maintenance/environment/skills/evo-reflow-handbook-parser - evo-reflow-json-output
tasks-evolved/manufacturing-equipment-maintenance/environment/skills/evo-reflow-json-output - evo-reflow-thermal-analysis
tasks-evolved/manufacturing-equipment-maintenance/environment/skills/evo-reflow-thermal-analysis - evo-fjsp-data-io
tasks-evolved/manufacturing-fjsp-optimization/environment/skills/evo-fjsp-data-io - evo-fjsp-scheduler
tasks-evolved/manufacturing-fjsp-optimization/environment/skills/evo-fjsp-scheduler - evo-fjsp-validator
tasks-evolved/manufacturing-fjsp-optimization/environment/skills/evo-fjsp-validator - evo-template-matching-counter
tasks-evolved/mario-coin-counting/environment/skills/evo-template-matching-counter - evo-video-keyframe-extraction
tasks-evolved/mario-coin-counting/environment/skills/evo-video-keyframe-extraction - evo-mars-clustering-eval
tasks-evolved/mars-clouds-clustering/environment/skills/evo-mars-clustering-eval - evo-mars-grid-search
tasks-evolved/mars-clouds-clustering/environment/skills/evo-mars-grid-search - evo-mars-pareto-output
tasks-evolved/mars-clouds-clustering/environment/skills/evo-mars-pareto-output - evo-dubbing-audio-processing
tasks-evolved/multilingual-video-dubbing/environment/skills/evo-dubbing-audio-processing - evo-dubbing-mux-report
tasks-evolved/multilingual-video-dubbing/environment/skills/evo-dubbing-mux-report - evo-dubbing-tts-synthesis
tasks-evolved/multilingual-video-dubbing/environment/skills/evo-dubbing-tts-synthesis - evo-docx-template-filler
tasks-evolved/offer-letter-generator/environment/skills/evo-docx-template-filler - evo-document-classify-and-sort
tasks-evolved/organize-messy-files/environment/skills/evo-document-classify-and-sort - evo-document-text-extraction
tasks-evolved/organize-messy-files/environment/skills/evo-document-text-extraction - evo-pdf-content-extraction
tasks-evolved/paper-anonymizer/environment/skills/evo-pdf-content-extraction - evo-pdf-redaction-engine
tasks-evolved/paper-anonymizer/environment/skills/evo-pdf-redaction-engine - evo-parallel-batch-search
tasks-evolved/parallel-tfidf-search/environment/skills/evo-parallel-batch-search - evo-parallel-determinism
tasks-evolved/parallel-tfidf-search/environment/skills/evo-parallel-determinism - evo-parallel-index-building
tasks-evolved/parallel-tfidf-search/environment/skills/evo-parallel-index-building - evo-tpp-solver
tasks-evolved/pddl-tpp-planning/environment/skills/evo-tpp-solver - evo-dataframe-diff-report
tasks-evolved/pdf-excel-diff/environment/skills/evo-dataframe-diff-report - evo-pdf-excel-extraction
tasks-evolved/pdf-excel-diff/environment/skills/evo-pdf-excel-extraction - evo-pedestrian-vlm-counting
tasks-evolved/pedestrian-traffic-counting/environment/skills/evo-pedestrian-vlm-counting - evo-video-frame-extraction
tasks-evolved/pedestrian-traffic-counting/environment/skills/evo-video-frame-extraction - evo-tts-audiobook-synth
tasks-evolved/pg-essay-to-audiobook/environment/skills/evo-tts-audiobook-synth - evo-web-essay-scraper
tasks-evolved/pg-essay-to-audiobook/environment/skills/evo-web-essay-scraper - evo-openpyxl-sheet-processor
tasks-evolved/powerlifting-coef-calc/environment/skills/evo-openpyxl-sheet-processor - evo-powerlifting-dots-formula
tasks-evolved/powerlifting-coef-calc/environment/skills/evo-powerlifting-dots-formula - evo-pptx-reference-slide
tasks-evolved/pptx-reference-formatting/environment/skills/evo-pptx-reference-slide - evo-pptx-title-detect-format
tasks-evolved/pptx-reference-formatting/environment/skills/evo-pptx-title-detect-format - evo-pptx-xml-io
tasks-evolved/pptx-reference-formatting/environment/skills/evo-pptx-xml-io - evo-protein-expression-analysis
tasks-evolved/protein-expression-analysis/environment/skills/evo-protein-expression-analysis - evo-proteomics-excel-formulas
tasks-evolved/protein-expression-analysis/environment/skills/evo-proteomics-excel-formulas - evo-scala-idiom-mapping
tasks-evolved/python-scala-translation/environment/skills/evo-scala-idiom-mapping - evo-scala-tokenizer-generator
tasks-evolved/python-scala-translation/environment/skills/evo-scala-tokenizer-generator - evo-dicke-model-simulation
tasks-evolved/quantum-numerical-simulation/environment/skills/evo-dicke-model-simulation - evo-wigner-csv-export
tasks-evolved/quantum-numerical-simulation/environment/skills/evo-wigner-csv-export - evo-r2r-linearization
tasks-evolved/r2r-mpc-control/environment/skills/evo-r2r-linearization - evo-r2r-mpc-controller
tasks-evolved/r2r-mpc-control/environment/skills/evo-r2r-mpc-controller - evo-nextjs-api-optimization
tasks-evolved/react-performance-debugging/environment/skills/evo-nextjs-api-optimization - evo-nextjs-bundle-reduction
tasks-evolved/react-performance-debugging/environment/skills/evo-nextjs-bundle-reduction - evo-nextjs-render-optimization
tasks-evolved/react-performance-debugging/environment/skills/evo-nextjs-render-optimization - evo-excel-data-extraction
tasks-evolved/reserves-at-risk-calc/environment/skills/evo-excel-data-extraction - evo-excel-financial-formulas
tasks-evolved/reserves-at-risk-calc/environment/skills/evo-excel-financial-formulas - evo-sales-pivot-analysis
tasks-evolved/sales-pivot-analysis/environment/skills/evo-sales-pivot-analysis - evo-sec13f-analyzer
tasks-evolved/sec-financial-report/environment/skills/evo-sec13f-analyzer - evo-seismic-data-preprocessing
tasks-evolved/seismic-phase-picking/environment/skills/evo-seismic-data-preprocessing - evo-seismic-phase-picking
tasks-evolved/seismic-phase-picking/environment/skills/evo-seismic-phase-picking - evo-atheris-fuzz-driver
tasks-evolved/setup-fuzzing-py/environment/skills/evo-atheris-fuzz-driver - evo-fuzz-env-runner
tasks-evolved/setup-fuzzing-py/environment/skills/evo-fuzz-env-runner - evo-python-library-discovery
tasks-evolved/setup-fuzzing-py/environment/skills/evo-python-library-discovery - evo-macro-demand-shock-scenarios
tasks-evolved/shock-analysis-demand/environment/skills/evo-macro-demand-shock-scenarios - evo-macro-sut-import-share
tasks-evolved/shock-analysis-demand/environment/skills/evo-macro-sut-import-share - evo-macro-weo-data
tasks-evolved/shock-analysis-demand/environment/skills/evo-macro-weo-data - evo-simpo-code-reproduction
tasks-evolved/simpo-code-reproduction/environment/skills/evo-simpo-code-reproduction - evo-software-dependency-audit
tasks-evolved/software-dependency-audit/environment/skills/evo-software-dependency-audit - evo-speaker-diarization-subtitles
tasks-evolved/speaker-diarization-subtitles/environment/skills/evo-speaker-diarization-subtitles - evo-spring-boot-jakarta-migration
tasks-evolved/spring-boot-jakarta-migration/environment/skills/evo-spring-boot-jakarta-migration - evo-suricata-custom-exfil
tasks-evolved/suricata-custom-exfil/environment/skills/evo-suricata-custom-exfil - evo-syzkaller-ppdev-syzlang
tasks-evolved/syzkaller-ppdev-syzlang/environment/skills/evo-syzkaller-ppdev-syzlang - evo-cluster-naming
tasks-evolved/taxonomy-tree-merge/environment/skills/evo-cluster-naming - evo-semantic-hierarchical-clustering
tasks-evolved/taxonomy-tree-merge/environment/skills/evo-semantic-hierarchical-clustering - evo-taxonomy-data-pipeline
tasks-evolved/taxonomy-tree-merge/environment/skills/evo-taxonomy-data-pipeline - evo-threejs-scene-parser
tasks-evolved/threejs-structure-parser/environment/skills/evo-threejs-scene-parser - evo-threejs-obj-export
tasks-evolved/threejs-to-obj/environment/skills/evo-threejs-obj-export - evo-threejs-to-obj
tasks-evolved/threejs-to-obj/environment/skills/evo-threejs-to-obj - evo-travel-data-search
tasks-evolved/travel-planning/environment/skills/evo-travel-data-search - evo-travel-itinerary-builder
tasks-evolved/travel-planning/environment/skills/evo-travel-itinerary-builder - evo-travel-planning
tasks-evolved/travel-planning/environment/skills/evo-travel-planning - evo-trend-anomaly-causal-inference
tasks-evolved/trend-anomaly-causal-inference/environment/skills/evo-trend-anomaly-causal-inference - evo-video-filler-word-remover
tasks-evolved/video-filler-word-remover/environment/skills/evo-video-filler-word-remover - evo-video-tutorial-indexer
tasks-evolved/video-tutorial-indexer/environment/skills/evo-video-tutorial-indexer - evo-pddl-plan-formatter
tasks-evolved/virtualhome-agent-planning/environment/skills/evo-pddl-plan-formatter - evo-pddl-solver
tasks-evolved/virtualhome-agent-planning/environment/skills/evo-pddl-solver - evo-virtualhome-agent-planning
tasks-evolved/virtualhome-agent-planning/environment/skills/evo-virtualhome-agent-planning - evo-excel-gcc-net-exports-formulas
tasks-evolved/weighted-gdp-calc/environment/skills/evo-excel-gcc-net-exports-formulas - evo-excel-workbook-formula-io
tasks-evolved/weighted-gdp-calc/environment/skills/evo-excel-workbook-formula-io - evo-excel-io
tasks-evolved/xlsx-recover-data/environment/skills/evo-excel-io - evo-nasa-budget-recovery
tasks-evolved/xlsx-recover-data/environment/skills/evo-nasa-budget-recovery - evo-xlsx-recover-data
tasks-evolved/xlsx-recover-data/environment/skills/evo-xlsx-recover-data
How it works
evo-3d-scan-calc
When your agent uses it
Complete pipeline for binary STL parsing, connected component extraction, volume computation, material density lookup, and mass calculation with JSON output.
What it loads into context
Frontmatter
38 tokensAlways available to the agent
SKILL.md
727 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Pipeline Overview
- Critical Details
- Usage
Scripts executed separately
scripts/utils.py
Files
SKILL.mdcore2,899 bytesSKILL.mdcore2,899 bytesSKILL.mdcore2,899 bytesscripts/utils.pyruns9,493 bytes
Read SKILL.md
# evo-3d-scan-calc
End-to-end skill for computing the mass of a 3D printed part from a binary STL scan file.
## Pipeline Overview
1. **Parse binary STL** — Decode 80-byte header, 4-byte triangle count, and 50-byte facet records. Extract vertices and Material ID (uint16 attribute field) per triangle.
2. **Find connected components** — Build vertex-based adjacency (triangles sharing any vertex are connected) using vertices quantized to **4 decimal places**. BFS to find all components.
3. **Select main part** — Compute volume for each component. The **largest by volume** is the main part.
4. **Extract Material ID** — Use the attribute from the **first triangle** of the largest component.
5. **Lookup density** — Reference the material density table: `{1: 0.10, 10: 7.85, 25: 2.70, 42: 5.55, 99: 11.34}`.
6. **Calculate mass** — `mass = volume * density`. **No unit conversion needed** (density table matches mesh coordinate units).
7. **Write report** — Save JSON with `main_part_mass` and `material_id`.
View the complete source on GitHubevo-mass-report-output
When your agent uses it
Orchestrates the full pipeline from STL parsing to JSON mass report output. Coordinates parsing, component analysis, volume computation, unit conversion, and mass calculation.
What it loads into context
Frontmatter
41 tokensAlways available to the agent
SKILL.md
399 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Pipeline
- Key Functions
- Usage
Scripts executed separately
scripts/utils.py
Files
SKILL.mdcore1,674 bytesSKILL.mdcore1,674 bytesscripts/utils.pyruns3,711 bytes
Read SKILL.md
# evo-mass-report-output
End-to-end pipeline orchestrator for mass calculation from binary STL files.
## Pipeline
1. Parse binary STL -> triangles with material IDs
2. Find largest connected component (vertex-based adjacency, 4-decimal quantization)
3. Extract Material ID from first triangle of largest component
4. Look up density from material density table
5. Compute volume (mm³) using signed tetrahedron method
6. Convert mm³ to cm³ (divide by 1000)
7. Mass = volume_cm³ × density_g/cm³
8. Round to 2 decimal places
9. Write JSON: {"main_part_mass": X.XX, "material_id": N}View the complete source on GitHubevo-mesh-geometry-analysis
When your agent uses it
Performs connected component analysis on triangle meshes using BFS with vertex adjacency and computes mesh volume via the signed tetrahedron method. Handles unit conversion and mass calculation.
What it loads into context
Frontmatter
41 tokensAlways available to the agent
SKILL.md
337 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Key Functions
- Usage
- Critical Details
Scripts executed separately
scripts/utils.py
Files
SKILL.mdcore1,346 bytesSKILL.mdcore1,346 bytesscripts/utils.pyruns3,368 bytes
Read SKILL.md
# evo-mesh-geometry-analysis
Mesh topology and volume computation.
## Key Functions
- `get_largest_connected_component(triangles, rounding_decimals=4)` - Find largest connected component via vertex-based BFS adjacency with 4-decimal quantization
- `compute_mesh_volume(triangles)` - Volume via signed tetrahedron method: abs(sum(v1.(v2×v3)))/6.0
- `convert_volume_mm3_to_cm3(volume_mm3)` - Divide by 1000
- `calculate_mass(volume_cm3, density_g_cm3)` - Mass = Volume × Density
## Usage
```pythonView the complete source on GitHubevo-stl-binary-parser
When your agent uses it
Parses binary STL files using Python's struct module, extracting triangle vertices, normals, and the 2-byte attribute byte count (used as Material ID). Provides filtering by Material ID and density table parsing.
What it loads into context
Frontmatter
51 tokensAlways available to the agent
SKILL.md
360 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Key Functions
- Usage
- Binary STL Layout
Scripts executed separately
scripts/utils.py
Files
SKILL.mdcore1,421 bytesSKILL.mdcore1,421 bytesscripts/utils.pyruns3,910 bytes
Read SKILL.md
# evo-stl-binary-parser
Parses binary STL files and material density tables.
## Key Functions
- `parse_binary_stl(filepath)` - Parse binary STL, returns list of (v1, v2, v3, material_id) tuples
- `parse_material_density_table(filepath)` - Parse markdown density table, returns {id: density} dict
- `filter_facets_by_material_id(triangles, material_id)` - Filter triangles by material
- `detect_material_id(triangles)` - Find dominant material ID (excluding debris ID=1)
- `lookup_density(material_id, density_table=None)` - Look up density from table
## Usage
View the complete source on GitHubevo-adaptive-cruise-control
When your agent uses it
Complete Adaptive Cruise Control simulation system with PID controllers, single-loop ACC architecture (cruise/follow/emergency modes), TTC safety, Euler integration simulation, and full I/O pipeline.
What it loads into context
Frontmatter
49 tokensAlways available to the agent
SKILL.md
1,075 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Overview
- Quick Start
- File Descriptions
- Key Design Decisions
- Tuning Gains (Pre-tuned)
Scripts executed separately
scripts/acc_system.pyscripts/pid_controller.pyscripts/simulation.pyscripts/tuning.py
Files
SKILL.mdcore4,175 bytesSKILL.mdcore4,175 bytesSKILL.mdcore4,175 bytesSKILL.mdcore4,175 bytesSKILL.mdcore4,175 bytesscripts/acc_system.pyruns7,771 bytesscripts/pid_controller.pyruns3,539 bytesscripts/simulation.pyruns9,789 bytesscripts/tuning.pyruns1,160 bytes
Read SKILL.md
# evo-adaptive-cruise-control
## Overview
A unified ACC simulation skill combining:
1. **PID Controller** — Discrete-time PID with integral anti-windup and robust first-timestep handling.
2. **ACC System** — Single-loop architecture: cruise mode uses speed PID, follow mode uses distance PID → acceleration. Three modes: cruise, follow, emergency. TTC-based safety override.
3. **Simulation Runner** — 1501-step Euler integration loop, sensor_data.csv / vehicle_params.yaml ingestion, tuning_results.yaml loading, simulation_results.csv output (with proper NaN→empty handling), and acc_report.md generation.
4. **Tuning** — Pre-tuned PID gains for speed and distance control.
## Quick Start
```bash
# 1. Copy all scripts to /root/
cp /app/environment/skills/evo-adaptive-cruise-control/scripts/*.py /root/View the complete source on GitHubevo-azure-bgp-oscillation-route-leak
When your agent uses it
Analyzes Azure Virtual WAN multi-hub BGP topologies to detect route oscillation (preference cycles) and valley-free route leak violations (Gao-Rexford model), then evaluates proposed solutions against domain-specific resolution criteria.
What it loads into context
Frontmatter
63 tokensAlways available to the agent
SKILL.md
703 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Domain Knowledge
- Usage
- Scripts
Scripts executed separately
scripts/utils.py
Files
SKILL.mdcore3,131 bytesSKILL.mdcore3,131 bytesscripts/utils.pyruns23,111 bytes
Read SKILL.md
# BGP Route Oscillation and Route Leak Analyzer for Azure Virtual WAN
Detects BGP route oscillation and valley-free route leak violations in Azure Virtual WAN multi-hub topologies, then evaluates whether proposed solutions resolve each issue.
## Domain Knowledge
### Oscillation Detection (Preference Cycle)
A BGP oscillation occurs when ASes form a mutual routing preference cycle: e.g., AS A prefers routes via AS B, while AS B prefers routes via AS A. The preference graph is a directed functional graph (out-degree ≤ 1 per node). A cycle of any length causes persistent non-convergence. Detection uses DFS-based traversal with path tracking.
**Output**: `oscillation_cycle` and `affected_ases` are deterministically ordered (rotated so the smallest ASN appears first).
### Route Leak Detection (Gao-Rexford Valley-Free Model)
Under the Gao-Rexford valley-free routing principle (RFC 7908):
- **Customer-learned** routes → may export to anyone (customers, peers, providers)View the complete source on GitHubevo-bibtex-parser
When your agent uses it
Parses BibTeX files using bibtexparser 1.4.2 and cleans LaTeX/BibTeX artifacts from fields like title, author, year, DOI, and venue. Produces a normalized list of citation dictionaries ready for verification.
What it loads into context
Frontmatter
61 tokensAlways available to the agent
SKILL.md
308 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Key Functions
- Usage
- Notes
Scripts executed separately
scripts/utils.py
Files
SKILL.mdcore1,204 bytesSKILL.mdcore1,204 bytesscripts/utils.pyruns2,954 bytes
Read SKILL.md
# evo-bibtex-parser
Parses BibTeX files and cleans LaTeX artifacts for citation verification.
## Key Functions
- `parse_bibtex_file(file_path)` - Parse a .bib file, returns list of entry dicts
- `clean_bibtex_artifacts(text)` - Remove {}, \commands, LaTeX escapes from strings
- `extract_citation_metadata(entries)` - Extract and clean metadata from parsed entries
## Usage
```python
import sysView the complete source on GitHubevo-citation-scorer
When your agent uses it
Compares parsed BibTeX citation metadata against API results using fuzzy string matching and multi-factor scoring to classify citations as real or fake, then outputs the final JSON report.
What it loads into context
Frontmatter
45 tokensAlways available to the agent
SKILL.md
310 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Key Functions
- Classification Logic
- Usage
Scripts executed separately
scripts/utils.py
Files
SKILL.mdcore1,324 bytesSKILL.mdcore1,324 bytesscripts/utils.pyruns5,999 bytes
Read SKILL.md
# evo-citation-scorer
Scores and classifies citations as real or fake.
## Key Functions
- `normalize_string(text)` - Normalize for comparison (lowercase, no punctuation)
- `calculate_title_similarity(title1, title2)` - Token-based title similarity (0-100)
- `compute_composite_score(citation, api_result)` - Multi-factor score (title 50%, author 30%, year 20%)
- `classify_citation(verification_result)` - Classify as Real/Fake based on scores
- `export_fake_citations_json(fake_titles, output_file)` - Write sorted JSON output
## Classification Logic
View the complete source on GitHubevo-citation-verifier
When your agent uses it
Queries external academic APIs (CrossRef, Semantic Scholar, DBLP, doi.org) to verify whether a citation exists. Implements robust HTTP sessions with retry logic, exponential backoff, and rate limiting.
What it loads into context
Frontmatter
50 tokensAlways available to the agent
SKILL.md
290 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Key Functions
- Usage
Scripts executed separately
scripts/utils.py
Files
SKILL.mdcore1,172 bytesSKILL.mdcore1,172 bytesscripts/utils.pyruns7,826 bytes
Read SKILL.md
# evo-citation-verifier
Verifies citations against academic APIs.
## Key Functions
- `get_robust_session()` - Create requests session with retry/backoff
- `verify_doi_exists(doi, session)` - Check if DOI resolves via CrossRef
- `query_crossref(title, session)` - Search CrossRef by title
- `query_semantic_scholar(title, session)` - Search Semantic Scholar
- `query_dblp(title, session)` - Search DBLP
- `verify_citation(citation, session)` - Full verification pipeline for one citation
- `rate_limited_query(session, url, params, headers, delay)` - Rate-limited GET
View the complete source on GitHubevo-civ6-adjacency-rules
When your agent uses it
Encodes all Civ6 Gathering Storm district adjacency bonus rules, placement validity, population limits, and civ-specific modifiers.
What it loads into context
Frontmatter
37 tokensAlways available to the agent
SKILL.md
310 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Usage
- Key Functions
Scripts executed separately
scripts/utils.py
Files
SKILL.mdcore1,220 bytesSKILL.mdcore1,220 bytesscripts/utils.pyruns7,889 bytes
Read SKILL.md
# evo-civ6-adjacency-rules
Computes adjacency bonuses for Civ6 districts.
## Usage
```python
import sys
sys.path.insert(0, '/app/environment/skills/evo-civ6-adjacency-rules/scripts')
from utils import calculate_adjacency_bonus, is_valid_district_placement, max_specialty_districts, is_valid_city_center
bonus = calculate_adjacency_bonus(map_data, x, y, 'CAMPUS', placements, 'GENERIC')
valid = is_valid_district_placement(map_data, x, y, 'CAMPUS', city_center, placed_tiles)
max_d = max_specialty_districts(population)View the complete source on GitHubevo-civ6-map-parser
When your agent uses it
Parses .Civ6Map SQLite database files to extract map dimensions, terrain, features, resources, and river edge data. Provides hex coordinate utilities for odd-r pointy-top hex grid.
What it loads into context
Frontmatter
49 tokensAlways available to the agent
SKILL.md
367 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Usage
- Key Functions
Scripts executed separately
scripts/utils.py
Files
SKILL.mdcore1,298 bytesSKILL.mdcore1,298 bytesscripts/utils.pyruns6,302 bytes
Read SKILL.md
# evo-civ6-map-parser
Parses Civilization VI .Civ6Map files (SQLite databases) and provides hex grid utilities.
## Usage
```python
import sys
sys.path.insert(0, '/app/environment/skills/evo-civ6-map-parser/scripts')
from utils import parse_civ6map, get_hex_neighbors, hex_distance, is_land_tile, is_mountain, is_tile_river_adjacent, get_land_tiles
map_data = parse_civ6map('/path/to/map.Civ6Map')
neighbors = get_hex_neighbors(5, 3)
dist = hex_distance(0, 0, 3, 3)View the complete source on GitHubevo-civ6-placement-optimizer
When your agent uses it
Searches for optimal city center and district placements to maximize total adjacency bonuses in Civ6 scenarios.
What it loads into context
Frontmatter
30 tokensAlways available to the agent
SKILL.md
258 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Usage
- Key Functions
Scripts executed separately
scripts/utils.py
Files
SKILL.mdcore1,080 bytesSKILL.mdcore1,080 bytesscripts/utils.pyruns6,033 bytes
Read SKILL.md
# evo-civ6-placement-optimizer
Optimizes district placement for maximum adjacency bonuses.
## Usage
```python
import sys
sys.path.insert(0, '/app/environment/skills/evo-civ6-placement-optimizer/scripts')
from utils import load_scenario, find_optimal_placements, write_solution_json
sys.path.insert(0, '/app/environment/skills/evo-civ6-map-parser/scripts')
from utils import parse_civ6map
View the complete source on GitHubevo-pdf-field-inspector
When your agent uses it
Inspects PDF AcroForm fields - enumerates field names, types, values, and checkbox on-states. Essential for discovering exact internal field keys before filling.
What it loads into context
Frontmatter
44 tokensAlways available to the agent
SKILL.md
263 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Key Functions
- Usage
- SC-100 Field Name Pattern
Scripts executed separately
scripts/utils.py
Files
SKILL.mdcore1,113 bytesSKILL.mdcore1,113 bytesscripts/utils.pyruns3,008 bytes
Read SKILL.md
# evo-pdf-field-inspector
Inspects a PDF form to enumerate all AcroForm field names, types (text, checkbox, radio),
current values, and checkbox appearance states.
## Key Functions
- `enumerate_pdf_fields(pdf_path)` - Returns dict of all fields with type, value, flags
- `classify_field_type(field_obj)` - Classifies pypdf Field into human-readable type
- `get_checkbox_on_states(pdf_path)` - Returns dict mapping checkbox field names to their on-state
## Usage
```pythonView the complete source on GitHubevo-pdf-form-filler
When your agent uses it
Fills PDF AcroForm fields (text and checkboxes) using pypdf, sets NeedAppearances flag, and writes the output PDF. Handles checkbox state detection and proper value updates.
What it loads into context
Frontmatter
50 tokensAlways available to the agent
SKILL.md
405 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Key Functions
- Usage
- SC-100 Checkbox Notes
Scripts executed separately
scripts/utils.py
Files
SKILL.mdcore1,411 bytesSKILL.mdcore1,411 bytesscripts/utils.pyruns2,690 bytes
Read SKILL.md
# evo-pdf-form-filler
Fills a PDF AcroForm with provided data (text fields, checkboxes), sets the
/NeedAppearances flag, and writes the output PDF.
## Key Functions
- `fill_pdf_form(input_pdf, output_pdf, text_fields, checkbox_fields)` - Main entry point
- `set_need_appearances(writer)` - Sets /NeedAppearances on AcroForm root
- `fill_text_field(writer, field_name, value)` - Fill a single text field
- `fill_checkbox_field(writer, field_name, on_state)` - Check a single checkbox
## Usage
View the complete source on GitHubevo-crystallography-fraction-format
When your agent uses it
Converts floating-point fractional coordinates to clean rational fraction strings with bounded denominators (<=12), handling edge cases like near-zero/near-one wrapping and integer values.
What it loads into context
Frontmatter
44 tokensAlways available to the agent
SKILL.md
415 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Key Functions
- Usage
- Rules
Scripts executed separately
scripts/fraction_utils.py
Files
SKILL.mdcore1,524 bytesSKILL.mdcore1,524 bytesscripts/fraction_utils.pyruns1,862 bytes
Read SKILL.md
# evo-crystallography-fraction-format
Converts floating-point crystallographic fractional coordinates to rational fraction strings.
## Key Functions
- `float_to_fraction_string(val, max_den=12)` - Convert single float to fraction string
- `rationalize_coordinate_vector(coords, max_den=12)` - Convert 3-element coordinate vector to list of fraction strings
## Usage
```python
import sys
sys.path.insert(0, '/app/environment/skills/evo-crystallography-fraction-format/scripts')View the complete source on GitHubevo-crystallography-wyckoff-analysis
When your agent uses it
Parses CIF files using pymatgen, performs space group symmetry analysis via SpacegroupAnalyzer, and extracts Wyckoff position letters, multiplicities, and representative atom fractional coordinates from the symmetrized structure.
What it loads into context
Frontmatter
55 tokensAlways available to the agent
SKILL.md
518 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Dependencies
- Key Functions
- Usage
- Key Details
Scripts executed separately
scripts/utils.py
Files
SKILL.mdcore1,942 bytesSKILL.mdcore1,942 bytesscripts/utils.pyruns4,393 bytes
Read SKILL.md
# evo-crystallography-wyckoff-analysis
Analyzes CIF files for Wyckoff position multiplicities and coordinates.
## Dependencies
- evo-crystallography-fraction-format (for coordinate rationalization)
- pymatgen >= 2025.10.7
- sympy >= 1.14.0
## Key Functions
- `load_structure_from_cif(filepath, primitive=False)` - Load CIF file to Structure
- `get_symmetrized_structure(structure, symprec=0.1)` - Get symmetrized structure
- `extract_wyckoff_multiplicities(sym_struct)` - Get {letter: multiplicity} dictView the complete source on GitHubevo-network-stats-computation
When your agent uses it
Computes all network statistics from extracted packet features and writes to CSV.
What it loads into context
Frontmatter
24 tokensAlways available to the agent
SKILL.md
121 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Usage
Scripts executed separately
scripts/utils.py
Files
SKILL.mdcore561 bytesSKILL.mdcore561 bytesscripts/utils.pyruns5,971 bytes
Read SKILL.md
# evo-network-stats-computation
## Usage
```python
import sys
sys.path.insert(0, '/app/environment/skills/evo-network-stats-computation/scripts')
from utils import (compute_protocol_counts, compute_time_stats, compute_ppm_buckets,
compute_size_stats, compute_shannon_entropy, compute_graph_metrics,
compute_iat_metrics, compute_pcr_metrics, compute_flow_metrics,
determine_analysis_flags, write_stats_csv)
```View the complete source on GitHubevo-pcap-feature-extraction
When your agent uses it
Reads PCAP via Scapy PcapReader, extracts per-packet features into numpy arrays.
What it loads into context
Frontmatter
30 tokensAlways available to the agent
SKILL.md
129 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Usage
Scripts executed separately
scripts/utils.py
Files
SKILL.mdcore498 bytesSKILL.mdcore498 bytesscripts/utils.pyruns2,240 bytes
Read SKILL.md
# evo-pcap-feature-extraction
## Usage
```python
import sys
sys.path.insert(0, '/app/environment/skills/evo-pcap-feature-extraction/scripts')
from utils import parse_pcap_to_features
features = parse_pcap_to_features('/root/packets.pcap')
```
Returns dict with: timestamps, lengths, src_ips, dst_ips, src_ports, dst_ports, has_tcp/udp/icmp/arp/ip, protocol_strsView the complete source on GitHubevo-d3v6-stock-visualization
When your agent uses it
Generates the complete visualization.js file implementing a D3.js v6 force-simulation bubble chart with sector clustering, an interactive data table, tooltips, legends, and bidirectional click-based highlighting between chart and table.
What it loads into context
Frontmatter
57 tokensAlways available to the agent
SKILL.md
366 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Usage
- Functions
- Key Design Decisions
Scripts executed separately
scripts/utils.py
Files
SKILL.mdcore1,605 bytesSKILL.mdcore1,605 bytesscripts/utils.pyruns9,438 bytes
Read SKILL.md
# evo-d3v6-stock-visualization
Generates visualization.js with D3.js v6 force-simulation bubble chart, data table, and interactions.
## Usage
```python
import sys
sys.path.insert(0, '/app/environment/skills/evo-d3v6-stock-visualization/scripts')
from utils import generate_visualization_js
generate_visualization_js('/root/output/js/visualization.js')
```
View the complete source on GitHubevo-web-scaffold-generator
When your agent uses it
Python utility that creates the output directory structure, copies input data, downloads d3.v6.min.js locally, and writes the index.html and style.css files for the stock visualization dashboard.
What it loads into context
Frontmatter
47 tokensAlways available to the agent
SKILL.md
270 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Usage
- Functions
Scripts executed separately
scripts/utils.py
Files
SKILL.mdcore1,219 bytesSKILL.mdcore1,219 bytesscripts/utils.pyruns5,393 bytes
Read SKILL.md
# evo-web-scaffold-generator
Generates the web app scaffold: directory structure, data copying, D3.js library, HTML, and CSS.
## Usage
```python
import sys
sys.path.insert(0, '/app/environment/skills/evo-web-scaffold-generator/scripts')
from utils import setup_output_directory, copy_input_data, download_d3_library, generate_index_html, generate_style_css
setup_output_directory()
copy_input_data()
download_d3_library()View the complete source on GitHubevo-dialogue-dotgen
When your agent uses it
Generates Graphviz DOT visualization files from parsed dialogue graph structures using the graphviz 0.20.3 Python API.
What it loads into context
Frontmatter
34 tokensAlways available to the agent
SKILL.md
161 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Key Functions
- Usage
Scripts executed separately
scripts/dotgen_utils.py
Files
SKILL.mdcore664 bytesSKILL.mdcore664 bytesSKILL.mdcore664 bytesscripts/dotgen_utils.pyruns1,970 bytes
Read SKILL.md
# evo-dialogue-dotgen
Generates DOT visualization from dialogue graphs.
## Key Functions
- `generate_dot(graph: dict, output_path: str)` - Generate DOT file from graph
- `escape_label(text: str) -> str` - Safely escape text for DOT labels
- `style_node(node_type: str) -> dict` - Get visual styling by node type
## Usage
```python
import sys
sys.path.insert(0, "/app/environment/skills/evo-dialogue-dotgen/scripts")View the complete source on GitHubevo-dialogue-output
When your agent uses it
Serializes dialogue graph to JSON file and generates Graphviz DOT visualization. Handles UTF-8 encoding, DOT node styling by type, and edge labeling.
What it loads into context
Frontmatter
39 tokensAlways available to the agent
SKILL.md
111 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Key Functions
Scripts executed separately
scripts/__init__.pyscripts/utils.py
Files
SKILL.mdcore488 bytesSKILL.mdcore488 bytesscripts/__init__.pyruns71 bytesscripts/utils.pyruns995 bytes
Read SKILL.md
# Dialogue Output
Exports a dialogue graph to JSON and Graphviz DOT format.
## Key Functions
- `export_json(graph, path)` - Write graph to JSON with UTF-8
- `export_dot(graph, path)` - Generate DOT file with styled nodes
- `generate_dot_visualization(graph, path)` - Alias for export_dotView the complete source on GitHubevo-dialogue-parser
When your agent uses it
Parses dialogue script text into intermediate section structures using regex, then builds a validated JSON graph schema with typed nodes and edges. Handles section headers, speaker lines, numbered choices with optional tags, and edge targets.
What it loads into context
Frontmatter
50 tokensAlways available to the agent
SKILL.md
255 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Parsing Rules
- Output Schema
- Key Functions
Scripts executed separately
scripts/__init__.pyscripts/utils.py
Files
SKILL.mdcore1,090 bytesscripts/__init__.pyruns87 bytesscripts/utils.pyruns3,531 bytes
Read SKILL.md
# Dialogue Parser
This skill parses raw dialogue script text files into a structured JSON graph.
## Parsing Rules
- Section headers: `[NodeName]` on their own line
- Speaker lines: `Speaker: text -> Target` (target optional)
- Choice lines: `N. [OptionalTag] Choice text -> Target`
- Node type is "choice" if section has numbered choices, else "line"
## Output Schema
```json
{"nodes": [{"id": str, "text": str, "speaker": str, "type": str}], "edges": [{"from": str, "to": str, "text": str}]}
```View the complete source on GitHubevo-egomotion-dynamic-analysis
When your agent uses it
For consecutive sampled frame pairs, computes sparse optical flow, estimates camera egomotion via partial affine transform, and detects dynamic objects via homography-based motion compensation and frame differencing.
What it loads into context
Frontmatter
48 tokensAlways available to the agent
SKILL.md
490 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Key Functions
- Usage
- Motion Classification Rules
- Pipeline
Scripts executed separately
scripts/utils.py
Files
SKILL.mdcore1,853 bytesSKILL.mdcore1,853 bytesscripts/utils.pyruns4,574 bytes
Read SKILL.md
# evo-egomotion-dynamic-analysis
Analyzes consecutive grayscale frame pairs to classify camera motion and detect dynamic objects.
## Key Functions
- `compute_egomotion_labels(prev_gray, curr_gray, th_trans=2.0, th_scale=0.015, th_rot=0.01)`
Returns `(labels, good_prev, good_curr)` where labels is a list of motion strings.
- `detect_dynamic_objects(prev_gray, curr_gray, good_prev, good_curr)`
Returns boolean mask (H,W) where True = dynamic pixel.
- `analyze_frame_pairs(frames)`
Processes all consecutive pairs. Returns `(motion_labels, dynamic_masks)`.View the complete source on GitHubevo-output-serialization
When your agent uses it
Serializes egomotion labels to JSON with frame-interval keys and binary masks to NPZ in CSR sparse format using only NumPy.
What it loads into context
Frontmatter
37 tokensAlways available to the agent
SKILL.md
381 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Key Functions
- Usage
- CSR Format Details
- JSON Format
Scripts executed separately
scripts/utils.py
Files
SKILL.mdcore1,421 bytesSKILL.mdcore1,421 bytesscripts/utils.pyruns2,127 bytes
Read SKILL.md
# evo-output-serialization
Serializes analysis results to the required output formats.
## Key Functions
- `dense_to_csr_manual(dense_mask)` — Converts 2D bool array to CSR (data, indices, indptr)
- `save_csr_masks_npz(mask_list, output_file, shape)` — Saves masks to NPZ with CSR format
- `export_motion_labels_json(motion_results, output_path)` — Saves motion labels to JSON
## Usage
```python
import sysView the complete source on GitHubevo-video-sampling
When your agent uses it
Extracts frames from an MP4 video file at a specified target FPS using sequential reading. Returns sampled grayscale frames and their original frame indices.
What it loads into context
Frontmatter
37 tokensAlways available to the agent
SKILL.md
316 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Key Function
- Usage
- Implementation Details
Scripts executed separately
scripts/utils.py
Files
SKILL.mdcore1,258 bytesSKILL.mdcore1,258 bytesscripts/utils.pyruns1,310 bytes
Read SKILL.md
# evo-video-sampling
Extracts frames from an MP4 video at a target FPS using reliable sequential reading
(avoids unreliable CAP_PROP_POS_FRAMES seeking in compressed MP4s).
## Key Function
- `sample_video_frames(video_path, target_fps=6)` — Returns `(sampled_frames, frame_indices, original_fps)`
- `sampled_frames`: list of grayscale np.uint8 2D arrays
- `frame_indices`: list of original frame indices (0-based)
- `original_fps`: the video's native FPS
## Usage
View the complete source on GitHubevo-seismic-data-io
When your agent uses it
Loads MiniSEED waveform data and CSV station metadata, groups traces by station for 3-component processing, and provides station coordinate lookups.
What it loads into context
Frontmatter
39 tokensAlways available to the agent
SKILL.md
238 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Functions
- Usage
Scripts executed separately
scripts/utils.py
Files
SKILL.mdcore961 bytesSKILL.mdcore961 bytesscripts/utils.pyruns2,203 bytes
Read SKILL.md
# evo-seismic-data-io
Loads seismic waveform and station data using ObsPy and Pandas.
## Functions
- `load_waveforms(mseed_path)` - Returns ObsPy Stream
- `load_stations(csv_path)` - Returns pandas DataFrame
- `group_traces_by_station(stream)` - Returns dict of {net.sta: Stream}
- `get_station_dict(stations_df)` - Returns dict of {net.sta: {lat, lon, elev}}
## Usage
```pythonView the complete source on GitHubevo-seismic-phase-association
When your agent uses it
Associates phase picks from multiple stations into earthquake events using temporal clustering (DBSCAN) and travel-time validation with a uniform velocity model, then outputs event catalog as CSV.
What it loads into context
Frontmatter
44 tokensAlways available to the agent
SKILL.md
326 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Functions
- Usage
Scripts executed separately
scripts/utils.py
Files
SKILL.mdcore1,367 bytesSKILL.mdcore1,367 bytesscripts/utils.pyruns5,299 bytes
Read SKILL.md
# evo-seismic-phase-association
Associates P/S picks into earthquake events using DBSCAN clustering and moveout validation.
## Functions
- `associate_picks(picks_df, station_dict, vp, vs, eps_sec, min_picks)` - Main association
- `validate_cluster(cluster_df, station_dict, source_lat, source_lon, t0, vp, vs, tolerance)` - Validate picks
- `estimate_origin_time(valid_picks, station_dict, source_lat, source_lon, vp, vs)` - Estimate t0
- `deduplicate_events(events, time_threshold)` - Remove duplicate events
- `write_event_catalog(events, output_path)` - Write CSV with ISO timestamps
## Usage
View the complete source on GitHubevo-seismic-phase-picking
When your agent uses it
Runs SeisBench deep learning models (PhaseNet/EQTransformer) on grouped station waveforms to produce P and S phase picks with timestamps and probabilities.
What it loads into context
Frontmatter
42 tokensAlways available to the agent
SKILL.md
313 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Functions
- Usage
Scripts executed separately
scripts/utils.py
Files
SKILL.mdcore1,293 bytesSKILL.mdcore1,293 bytesscripts/utils.pyruns2,967 bytes
Read SKILL.md
# evo-seismic-phase-picking
Uses SeisBench PhaseNet/EQTransformer for P/S wave picking.
## Functions
- `load_picker_model(model_name, weights)` - Load pretrained SeisBench model
- `pick_phases_for_stream(model, stream_3c, p_threshold, s_threshold)` - Pick one station
- `pick_all_stations(model, station_streams, p_threshold, s_threshold)` - Pick all stations
- `picks_to_dataframe(picks_list)` - Convert picks to DataFrame with unix_time column
## Usage
Note: Since all skills have utils.py, use importlib to avoid name collisions:View the complete source on GitHubevo-geospatial-antimeridian-plates
When your agent uses it
Load and process PB2002 tectonic plate boundaries and polygons with antimeridian-safe coordinate normalization (0-360 longitude shift) using Shapely 2.0 transform and GeoPandas 1.0 APIs.
What it loads into context
Frontmatter
58 tokensAlways available to the agent
SKILL.md
642 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Key Concepts
- Functions
- Usage
Scripts executed separately
scripts/utils.py
Files
SKILL.mdcore2,461 bytesSKILL.mdcore2,461 bytesscripts/utils.pyruns3,302 bytes
Read SKILL.md
# evo-geospatial-antimeridian-plates
Handles loading PB2002 tectonic plate polygon and boundary GeoJSON files, filtering by plate code, and normalizing coordinates across the antimeridian to 0-360 range.
## Key Concepts
### Antimeridian Problem
The Pacific plate spans the 180°/-180° antimeridian. Standard WGS84 coordinates wrap at this boundary, causing catastrophic topological artifacts when projecting. Solution: shift all negative longitudes by +360 to create a continuous 0°-360° space.
### PB2002 Data Model
- **Plates file** (`PB2002_plates.json`): Contains Polygon/MultiPolygon geometries. Pacific plate identified by `Code == 'PA'`.
- **Boundaries file** (`PB2002_boundaries.json`): Contains LineString geometries. Each segment has `PlateA` and `PlateB` properties. Pacific boundaries are where `PlateA == 'PA'` OR `PlateB == 'PA'`.
### Coordinate HandlingView the complete source on GitHubevo-geospatial-earthquake-distance
When your agent uses it
Parse USGS earthquake GeoJSON, spatially filter earthquakes within a tectonic plate, compute projected distances to plate boundaries using EPSG:3832, and output the furthest earthquake as formatted JSON.
What it loads into context
Frontmatter
51 tokensAlways available to the agent
SKILL.md
643 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Key Concepts
- Functions
- Usage
Scripts executed separately
scripts/utils.py
Files
SKILL.mdcore2,471 bytesSKILL.mdcore2,471 bytesscripts/utils.pyruns5,849 bytes
Read SKILL.md
# evo-geospatial-earthquake-distance
Complete pipeline for finding the earthquake furthest from a tectonic plate boundary within the plate.
## Key Concepts
### USGS GeoJSON Format
- Root: FeatureCollection with `features` array
- Each feature: `id` (string), `properties` (mag, place, time in ms epoch), `geometry` (Point with [lon, lat, depth])
- Time is milliseconds since Unix epoch, convert with `pd.to_datetime(ms, unit='ms', utc=True)`
- ISO 8601 format: `strftime('%Y-%m-%dT%H:%M:%SZ')`
### Pipeline Steps
1. Parse earthquakes, store original lat/lon, shift geometry to 0-360View the complete source on GitHubevo-macro-cycle-correlation
When your agent uses it
Deflates nominal series to real values using CPI, applies log transformation and Hodrick-Prescott filter to extract cyclical components, and computes Pearson correlation between two cyclical series.
What it loads into context
Frontmatter
47 tokensAlways available to the agent
SKILL.md
579 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Key Functions
- Usage
- Technical Details
Scripts executed separately
scripts/utils.py
Files
SKILL.mdcore2,274 bytesSKILL.mdcore2,274 bytesscripts/utils.pyruns5,437 bytes
Read SKILL.md
# evo-macro-cycle-correlation
Deflates nominal macroeconomic series, applies HP filter for cycle extraction, and computes Pearson correlation between cyclical components.
## Key Functions
### `deflate_nominal_to_real(nominal, cpi)`
Converts nominal to real values: Real_t = (Nominal_t / CPI_t) * 100
### `extract_hp_cycle(real_series, lamb=100)`
Applies np.log() then HP filter (statsmodels hpfilter) to extract cyclical component.
- Uses natural log (np.log, NOT np.log10)
- hpfilter returns (cycle, trend) - parameter name is `lamb`
- lamb=100 for annual data (standard)View the complete source on GitHubevo-macro-data-ingestion
When your agent uses it
Parses ERP .xls tables and CPI .xlsx files, handles multi-row headers, extracts annual totals, computes partial-year averages from quarterly data, and produces clean annual series indexed by integer year.
What it loads into context
Frontmatter
49 tokensAlways available to the agent
SKILL.md
611 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Key Functions
- Usage
- Data Format Notes
Scripts executed separately
scripts/data_ingestion.pyscripts/utils.py
Files
SKILL.mdcore2,284 bytesSKILL.mdcore2,284 bytesscripts/data_ingestion.pyruns6,609 bytesscripts/utils.pyruns6,609 bytes
Read SKILL.md
# evo-macro-data-ingestion
Parses Economic Report of the President (ERP) `.xls` tables and CPI `.xlsx` files into clean pandas Series indexed by integer year.
## Key Functions
### `parse_erp_annual_total(filepath, target_year=2024)`
Parses an ERP .xls file to extract the annual "Total" column (first data column).
- Handles multi-row headers, trailing periods on years (e.g., '1973.')
- Handles quarterly data at bottom of table
- For partial years (e.g., 2024 with Q1-Q3 only), computes average of available quarters
- Uses `engine="xlrd"` for .xls files
- Returns: pd.Series indexed by integer year
View the complete source on GitHubevo-acopf-network-parser
When your agent uses it
Parses Matpower-style network.json files into Python data structures suitable for ACOPF formulation.
What it loads into context
Frontmatter
28 tokensAlways available to the agent
SKILL.md
245 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Usage
- Key Details
Scripts executed separately
scripts/utils.py
Files
SKILL.mdcore1,045 bytesSKILL.mdcore1,045 bytesscripts/utils.pyruns6,191 bytes
Read SKILL.md
# evo-acopf-network-parser
Parses Matpower-style network.json (array format) into solver-ready structures.
## Usage
```python
import sys
sys.path.insert(0, '/app/environment/skills/evo-acopf-network-parser/scripts')
from utils import parse_network_json, map_generators_to_buses, identify_reference_buses, get_branch_bus_mappings
baseMVA, buses, gens, branches, loads_by_bus, shunts_by_bus = parse_network_json('network.json')
gen_at_bus = map_generators_to_buses(gens, buses)
ref_buses = identify_reference_buses(buses)
branch_from, branch_to = get_branch_bus_mappings(branches, buses)
```View the complete source on GitHubevo-acopf-report-generator
When your agent uses it
Extracts ACOPF solution values, computes derived quantities, and produces structured report.json.
What it loads into context
Frontmatter
28 tokensAlways available to the agent
SKILL.md
175 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Usage
- Key Details
Scripts executed separately
scripts/utils.py
Files
SKILL.mdcore778 bytesSKILL.mdcore778 bytesscripts/utils.pyruns6,858 bytes
Read SKILL.md
# evo-acopf-report-generator
Extracts solution from solved Pyomo ACOPF model and generates report.json.
## Usage
```python
import sys
sys.path.insert(0, '/app/environment/skills/evo-acopf-report-generator/scripts')
from utils import generate_report_json
report = generate_report_json(model, baseMVA, results, output_path='report.json', top_n_branches=5)
```
## Key Details
- Converts per-unit values to MW/MVAr/degreesView the complete source on GitHubevo-acopf-solver
When your agent uses it
Builds and solves AC Optimal Power Flow using Pyomo+IPOPT with polar coordinate formulation.
What it loads into context
Frontmatter
28 tokensAlways available to the agent
SKILL.md
205 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Usage
- Key Details
Scripts executed separately
scripts/utils.py
Files
SKILL.mdcore854 bytesSKILL.mdcore854 bytesscripts/utils.pyruns6,675 bytes
Read SKILL.md
# evo-acopf-solver
Builds and solves full ACOPF problem using Pyomo and IPOPT.
## Usage
```python
import sys
sys.path.insert(0, '/app/environment/skills/evo-acopf-solver/scripts')
from utils import build_and_solve_acopf, build_acopf_model, solve_acopf, install_solver
model, results = build_and_solve_acopf(baseMVA, buses, gens, branches, loads_by_bus, shunts_by_bus,
gen_at_bus, branch_from, branch_to)
```
## Key DetailsView the complete source on GitHubevo-dcopf-solver
When your agent uses it
Solves DC-OPF with spinning reserve co-optimization using PuLP/CBC. Extracts LMPs from dual variables, reserve MCP, binding lines.
What it loads into context
Frontmatter
44 tokensAlways available to the agent
SKILL.md
344 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Key Functions
- Usage
Scripts executed separately
scripts/utils.py
Files
SKILL.mdcore1,369 bytesSKILL.mdcore1,369 bytesscripts/utils.pyruns6,607 bytes
Read SKILL.md
# evo-dcopf-solver
Solves DC-OPF with reserve co-optimization using PTDF formulation and PuLP.
## Key Functions
- `solve_dcopf_with_reserves(nb, ng, nl, gen_info, branches, costs, load_p, matrices, reserve_capacity, reserve_requirement, Cg)` - Main solver
- `extract_lmps(result, int2ext)` - Returns list of {bus, lmp_dollars_per_MWh}
- `extract_reserve_mcp(result)` - Returns reserve MCP float
- `identify_binding_lines(result, branches, int2ext, threshold=0.99)` - Returns binding line dicts
- `compute_total_cost(result)` - Returns total cost float
## Usage
View the complete source on GitHubevo-market-report
When your agent uses it
Compares base and counterfactual DC-OPF results, computes impact analysis, and exports report.json.
What it loads into context
Frontmatter
30 tokensAlways available to the agent
SKILL.md
245 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Key Functions
- Usage
Scripts executed separately
scripts/utils.py
Files
SKILL.mdcore999 bytesSKILL.mdcore999 bytesscripts/utils.pyruns2,745 bytes
Read SKILL.md
# evo-market-report
Compares scenarios and builds the final report.json.
## Key Functions
- `compute_impact_analysis(base_cost, cf_cost)` - Cost reduction
- `find_top_lmp_drops(base_lmps, cf_lmps, n=3)` - Top n buses with largest LMP drop
- `check_congestion_relieved(cf_binding, f_bus, t_bus)` - True if line not binding
- `build_report_json(...)` - Assembles complete report structure
- `export_report(report, filepath)` - Writes JSON file
## Usage
View the complete source on GitHubevo-matpower-parser
When your agent uses it
Parses MATPOWER JSON files into structured Python data with bus mapping, network matrix construction (A, Bbranch, Bbus, PTDF), branch modification, and generator cost parsing.
What it loads into context
Frontmatter
46 tokensAlways available to the agent
SKILL.md
507 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Key Functions
- Usage
Scripts executed separately
scripts/utils.py
Files
SKILL.mdcore1,913 bytesSKILL.mdcore1,913 bytesscripts/utils.pyruns5,733 bytes
Read SKILL.md
# evo-matpower-parser
Parses MATPOWER JSON network files and builds all data structures needed for DC-OPF.
## Key Functions
- `load_matpower_json(filepath)` - Load JSON file, returns dict
- `create_bus_mappings(bus_data)` - Returns (ext2int, int2ext) dicts
- `find_slack_bus(bus_data)` - Returns external bus ID of slack (type 3)
- `parse_generators(gen_data, ext2int)` - Returns dict with ng, gen_bus_int, pmax, pmin, status
- `parse_branches(branch_data, ext2int)` - Returns dict with nl, f/t_bus_int/ext, x, rate_a, status
- `parse_gencost(gencost_data)` - Returns dict with c2, c1, c0 arrays
- `compute_network_matrices(bus_data, branches, ext2int, slack_ext)` - Returns dict with PTDF, Bbus, etc.
- `modify_branch_rate(data, f_bus, t_bus, multiplier)` - Deep copies data, scales RATE_AView the complete source on GitHubevo-enterprise-doc-parser
When your agent uses it
Provides utility functions to discover files recursively in a directory and extract text content from diverse enterprise document formats including DOCX, XLSX, PPTX, PDF, and plain text files. Handles dependency installation, merged cells in Excel, presenter notes in PowerPoint, headers/footers in Word documents, and encoding detection.
What it loads into context
Frontmatter
73 tokensAlways available to the agent
SKILL.md
438 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Key Functions
- Usage
Scripts executed separately
scripts/utils.py
Files
SKILL.mdcore1,921 bytesSKILL.mdcore1,921 bytesscripts/utils.pyruns6,737 bytes
Read SKILL.md
# evo-enterprise-doc-parser
Utility functions for discovering and extracting text from enterprise document formats.
## Key Functions
- `ensure_dependencies(required_packages)` - Install missing Python packages at runtime (handles PEP 668/Ubuntu 24.04)
- `discover_files(root_dir)` - Recursively scan directory, return list of Path objects
- `extract_text_from_pdf(filepath)` - Extract text from PDF using PyMuPDF (fitz)
- `extract_text_from_docx(filepath)` - Extract text from DOCX including headers, footers, tables
- `extract_text_from_xlsx(filepath)` - Extract text from XLSX handling merged cells
- `extract_text_from_pptx(filepath)` - Extract text from PPTX including presenter notes
- `safe_read_text(filepath)` - Read text files with encoding detection fallback
- `process_file(filepath)` - Route file to appropriate extractor based on extensionView the complete source on GitHubevo-enterprise-qa-pipeline
When your agent uses it
Orchestrates the end-to-end question-answering pipeline for enterprise Slack data. Parses malformed question.txt files, searches extracted document text for answers (employee IDs, URLs, team member names), tracks token consumption, and writes the final answer.json output.
What it loads into context
Frontmatter
62 tokensAlways available to the agent
SKILL.md
364 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Key Functions
- Usage
- Depends On
Scripts executed separately
scripts/utils.py
Files
SKILL.mdcore1,643 bytesSKILL.mdcore1,643 bytesscripts/utils.pyruns8,267 bytes
Read SKILL.md
# evo-enterprise-qa-pipeline
End-to-end QA pipeline for enterprise Slack conversation data.
## Key Functions
- `parse_question_file(filepath)` - Parse malformed/unquoted JSON question file using YAML trick
- `extract_employee_ids(text)` - Extract employee IDs matching eid_XXXXXXXX pattern
- `extract_urls(text)` - Extract HTTP/HTTPS URLs from text
- `search_context_for_answer(messages, keywords, context_window)` - Search Slack messages for relevant context
- `find_report_authors_and_reviewers(product_data, report_name)` - Find who authored and reviewed a report
- `find_competitor_insight_providers(product_data, insight_type)` - Find who discussed competitor strengths/weaknesses
- `find_competitor_demo_urls(product_data)` - Find demo URLs for competitor products
- `count_tokens_for_text(text)` - Count tokens using tiktoken cl100k_base encodingView the complete source on GitHubevo-pptx-embedded-excel-updater
When your agent uses it
Provides utilities for finding and manipulating embedded Excel OLE objects within PPTX files, reading text boxes for context, modifying Excel cell values while preserving formulas, and saving the updated PPTX. Use when you need to extract embedded Excel spreadsheets from PowerPoint presentations, update exchange rates or other cell values based on text box annotations, replace embedded Excel data while keeping formula integrity, or perform any programmatic modification of OLE-embedded Excel objects in PPTX files.
What it loads into context
Frontmatter
106 tokensAlways available to the agent
SKILL.md
1,162 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Overview
- Requirements
- Key Domain Knowledge
- Usage
- Functions Reference
Scripts executed separately
scripts/utils.py
Files
SKILL.mdcore4,720 bytesSKILL.mdcore4,720 bytesscripts/utils.pyruns7,484 bytes
Read SKILL.md
# evo-pptx-embedded-excel-updater
## Overview
End-to-end handling of embedded Excel OLE objects in PPTX files. Covers:
- Identifying OLE shapes and text boxes on slides
- Extracting embedded xlsx blobs via python-pptx
- Reading/modifying Excel data with openpyxl while preserving formula cells
- Writing modified blobs back into the PPTX package
- Parsing text box content for updated exchange rate values
## Requirements
- python-pptx >= 1.0.2
- openpyxl >= 3.1.5
View the complete source on GitHubevo-tess-lightcurve-preprocessing
When your agent uses it
Load TESS text-format light curves and prepare them for transit detection by applying quality flag filtering, NaN removal, outlier rejection, normalization, and Savitzky-Golay flattening to remove stellar variability.
What it loads into context
Frontmatter
55 tokensAlways available to the agent
SKILL.md
296 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Usage
- Key rules
Scripts executed separately
scripts/utils.py
Files
SKILL.mdcore1,189 bytesSKILL.mdcore1,189 bytesscripts/utils.pyruns2,011 bytes
Read SKILL.md
# TESS Lightcurve Preprocessing
## Usage
```python
import sys
sys.path.insert(0, '/app/environment/skills/evo-tess-lightcurve-preprocessing/scripts')
from utils import load_tess_lightcurve, filter_quality_and_nans, remove_outliers, estimate_rotation_period, flatten_lightcurve
time, flux, flux_err = load_tess_lightcurve('/root/data/tess_lc.txt')
time, flux, flux_err = filter_quality_and_nans(time, flux, flux_err, quality)
time, flux, flux_err = remove_outliers(time, flux, flux_err, sigma=5)
rot_p = estimate_rotation_period(time, flux)
time_f, flux_f = flatten_lightcurve(time, flux, window_length=0.5)
```View the complete source on GitHubevo-transit-period-detection
When your agent uses it
Run BLS and/or Transit Least Squares (TLS) periodograms on a cleaned, flattened light curve to identify the exoplanet orbital period, and write the result to a properly formatted output file.
What it loads into context
Frontmatter
51 tokensAlways available to the agent
SKILL.md
188 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Usage
- Notes
Scripts executed separately
scripts/utils.py
Files
SKILL.mdcore805 bytesSKILL.mdcore805 bytesscripts/utils.pyruns1,810 bytes
Read SKILL.md
# Transit Period Detection
## Usage
```python
import sys
sys.path.insert(0, '/app/environment/skills/evo-transit-period-detection/scripts')
from utils import detect_transit_tls, detect_transit_bls, save_period
period, results = detect_transit_tls(time, flux)
save_period(period, '/root/period.txt')
```
## Notes
- TLS is preferred over BLS for small planets due to limb-darkening modeling.View the complete source on GitHubevo-excel-match-analyzer
When your agent uses it
Scores dice games and compares paired matches between players. Loads Excel dice roll data, computes scores using 6 scoring categories (high_and_often, summation, highs_and_lows, only_two_numbers, all_the_numbers, ordered_subset_of_four), finds optimal game scores by pairing different categories across 2 turns, then pairs odd/even games for head-to-head match comparison.
What it loads into context
Frontmatter
87 tokensAlways available to the agent
SKILL.md
863 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Usage
- Scoring Rules (6 Categories)
- Game Scoring
- Match Pairing
- Key Functions
Scripts executed separately
scripts/utils.py
Files
SKILL.mdcore3,122 bytesSKILL.mdcore3,122 bytesscripts/utils.pyruns6,995 bytes
Read SKILL.md
# Excel Match Analyzer
Analyzes dice game data from Excel files. Computes game scores using 6 scoring
categories, then pairs odd-numbered games (Player 1) vs even-numbered games
(Player 2) for match comparison.
## Usage
```python
import sys
sys.path.insert(0, '/app/environment/skills/evo-excel-match-analyzer/scripts')
from utils import (
load_excel_data, compute_all_game_scores, split_by_parity,
compare_paired_matches, compute_win_difference, write_answerView the complete source on GitHubevo-pdf-context-extractor
When your agent uses it
Extracts text from PDF files using pypdf 5.x. Use when you need to read PDF documents to understand background context, column definitions, and scoring rules for data analysis tasks.
What it loads into context
Frontmatter
49 tokensAlways available to the agent
SKILL.md
233 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Usage
- Key Functions
- Technical Notes
Scripts executed separately
scripts/utils.py
Files
SKILL.mdcore963 bytesSKILL.mdcore963 bytesscripts/utils.pyruns897 bytes
Read SKILL.md
# PDF Context Extractor
Extracts text content from PDF files using pypdf 5.x (PdfReader API).
## Usage
```python
import sys
sys.path.insert(0, '/app/environment/skills/evo-pdf-context-extractor/scripts')
from utils import extract_pdf_text, get_all_pages_text
# Get all text from a PDF
text = extract_pdf_text('/path/to/file.pdf')
View the complete source on GitHubWhen your agent uses it
What it loads into context
Frontmatter
0 tokensAlways available to the agent
SKILL.md
561 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Description
- Key Concepts
- Dependencies
- Usage
- Function Reference
- Notes
Scripts executed separately
scripts/utils.py
Files
SKILL.mdcore2,347 bytesSKILL.mdcore2,347 bytesscripts/utils.pyruns4,293 bytes
Read SKILL.md
# evo-molecule-similarity
## Description
Find top-k similar chemicals from a PDF molecule pool using Morgan fingerprints
with Tanimoto similarity. Converts chemical names to SMILES via PubChemPy,
computes Morgan fingerprints (radius=2, chirality=True), and ranks by
Tanimoto similarity with alphabetical tie-breaking.
## Key Concepts
- **PDF Extraction**: Uses pdfplumber to extract chemical names (one per line)
- **Name-to-SMILES**: Uses PubChemPy (external resource, no manual mapping)
- **Morgan Fingerprints**: radius=2, useChirality=True, default 2048 bits
- **Tanimoto Similarity**: Standard similarity metric for molecular fingerprints
- **Sorting**: Descending by similarity, alphabetical for ties
View the complete source on GitHubevo-build-diagnosis
When your agent uses it
Analyzes a Python repository to identify the root causes of build failures, including syntax errors, import errors, test failures, and build configuration issues. Use when diagnosing why a Python project fails to build or pass tests. Scans repository files for syntax errors via ast.parse/compile, parses pytest output and CI logs, checks build configuration files (pyproject.toml, setup.py, setup.cfg), identifies missing dependencies, and produces a structured diagnosis report.
What it loads into context
Frontmatter
101 tokensAlways available to the agent
SKILL.md
555 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- When to Use
- Workflow
- Key Functions
- Important Notes
- Reference
Scripts executed separately
scripts/diagnosis.py
Files
SKILL.mdcore2,525 bytesSKILL.mdcore2,525 bytesscripts/diagnosis.pyruns8,130 bytes
Read SKILL.md
# Build Diagnosis Skill
This skill analyzes Python repositories to identify root causes of build failures.
## When to Use
- A Python project fails to build or install
- pytest tests are failing with errors
- CI/CD pipelines report build failures
- You need to diagnose syntax errors, import errors, or configuration issues
## Workflow
1. **Find the repository** using `find_repo_path()` to locate the project rootView the complete source on GitHubevo-patch-generate-apply
When your agent uses it
Generates git-compatible unified diff patches from original and modified file contents, writes them to numbered patch files, and applies them to the repository using git apply or GNU patch. Use when you need to create code patches, apply fixes to source files, or automate code modifications via diff/patch workflow.
What it loads into context
Frontmatter
70 tokensAlways available to the agent
SKILL.md
467 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- When to Use
- Workflow
- Key Functions
- Important Notes
- Reference
Scripts executed separately
scripts/patch.py
Files
SKILL.mdcore2,005 bytesSKILL.mdcore2,005 bytesscripts/patch.pyruns4,034 bytes
Read SKILL.md
# Patch Generate & Apply Skill
Generates and applies unified diff patches for code fixes.
## When to Use
- You need to generate a patch file from code changes
- You need to apply a .diff/.patch file to a repository
- Automating code fixes via the diff/patch workflow
## Workflow
1. **Generate diff** using `generate_unified_diff()` with a/b prefixes
2. **Handle EOF** using `handle_no_newline_at_eof()` for POSIX complianceView the complete source on GitHubWhen your agent uses it
What it loads into context
Frontmatter
0 tokensAlways available to the agent
SKILL.md
380 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Description
- When to Use
- Common Patterns
- Usage
Scripts executed separately
scripts/utils.py
Files
SKILL.mdcore1,641 bytesSKILL.mdcore1,641 bytesSKILL.mdcore1,641 bytesSKILL.mdcore1,641 bytesSKILL.mdcore1,641 bytesscripts/utils.pyruns6,627 bytes
Read SKILL.md
# evo-python-build-fixer
## Description
Diagnoses and fixes Python repository build failures. Analyzes source code for
import errors, syntax errors, missing dependencies, and configuration issues.
Generates standard unified diff patches and applies them.
## When to Use
- When a Python project fails to build or pass tests
- When you need to diagnose import errors, missing optional dependencies
- When you need to create and apply git-compatible patches
## Common Patterns
### Pattern 1: Optional Dependency Import GuardView the complete source on GitHubevo-maven-build-diagnosis
When your agent uses it
Executes Maven builds, captures output, and parses error logs to identify root causes of build failures. Handles compilation errors, dependency resolution failures, POM configuration issues, and JDK version incompatibilities.
What it loads into context
Frontmatter
51 tokensAlways available to the agent
SKILL.md
547 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Key Functions
- Usage
- Common Error Patterns
Scripts executed separately
scripts/utils.py
Files
SKILL.mdcore2,308 bytesSKILL.mdcore2,308 bytesscripts/utils.pyruns9,979 bytes
Read SKILL.md
# evo-maven-build-diagnosis
Diagnoses Java Maven build failures by analyzing error logs and .travis.yml configuration.
## Key Functions
- `execute_maven_build(project_dir, goals, java_home, timeout_secs, pom_file)` - Run Maven build via subprocess
- `parse_compilation_errors(maven_log)` - Extract compilation errors with file/line/col/message
- `parse_dependency_errors(maven_log)` - Extract missing dependency artifacts
- `parse_plugin_errors(maven_log)` - Extract plugin execution failures
- `parse_pom_errors(maven_log)` - Extract POM-related errors (missing files, invalid XML)
- `parse_version_incompatibilities(maven_log)` - Extract source/target version issues
- `detect_java_version_from_pom(pom_path)` - Read Java version from pom.xml
- `classify_build_failure(maven_log)` - Classify the primary failure typeView the complete source on GitHubevo-maven-patch-generation
When your agent uses it
Generates GNU-compatible unified diff patches for proposed code or POM fixes, writes them to numbered patch files, and applies them to the repository.
What it loads into context
Frontmatter
39 tokensAlways available to the agent
SKILL.md
445 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Key Functions
- Usage
- Important Notes
Scripts executed separately
scripts/utils.py
Files
SKILL.mdcore1,819 bytesSKILL.mdcore1,819 bytesscripts/utils.pyruns4,967 bytes
Read SKILL.md
# evo-maven-patch-generation
Generates and applies unified diff patches for Java Maven build fixes.
## Key Functions
- `generate_unified_diff(original_text, modified_text, file_path)` - Basic unified diff
- `make_strict_patch(original_text, modified_text, file_path)` - Strict diff with EOF newline handling
- `write_patch_file(patch_content, patch_path)` - Write patch to disk
- `apply_patch_via_git(patch_path, project_dir)` - Apply via git apply
- `apply_patch_via_patch_command(patch_path, project_dir, strip)` - Apply via patch command
- `apply_patch(patch_path, project_dir)` - Try git apply, fallback to patch
- `modify_file_content(file_path, old_text, new_text)` - Simple text replacement
- `modify_java_source(file_path, modifications)` - Apply multiple replacements to Java fileView the complete source on GitHubevo-druid-cve-patch
When your agent uses it
Patches Apache Druid 0.20.0 for CVE-2021-25646 - a JavaScript injection vulnerability where empty-string keys in JSON payloads can override server-side JavaScriptConfig to enable arbitrary code exe...
What it loads into context
Frontmatter
59 tokensAlways available to the agent
SKILL.md
815 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Purpose
- Vulnerability Summary
- Patch Strategy (Two-Layer Defense)
- Affected Files
- Usage
- Build Command
- Key Lessons
Scripts executed separately
scripts/patch_druid.py
Files
SKILL.mdcore3,199 bytesSKILL.mdcore3,199 bytesSKILL.mdcore3,199 bytesSKILL.mdcore3,199 bytesscripts/patch_druid.pyruns7,857 bytes
Read SKILL.md
# Skill: evo-druid-cve-patch
## Purpose
Patches Apache Druid 0.20.0 for CVE-2021-25646 - a JavaScript injection vulnerability where
empty-string keys in JSON payloads can override server-side JavaScriptConfig to enable
arbitrary code execution.
## Vulnerability Summary
- **CVE**: CVE-2021-25646
- **Affected**: Apache Druid <= 0.20.0
- **Mechanism**: Empty key `""` in JSON overrides `@JacksonInject JavaScriptConfig` parameter
- **Impact**: Authenticated RCE via JavaScript filters/aggregators/extraction functions
## Patch Strategy (Two-Layer Defense)View the complete source on GitHubevo-erlang-ssh-cve-patch
When your agent uses it
Identifies and patches CVE-2025-32433 in Erlang/OTP SSH server source code by inserting an authentication-state check in ssh_connection.erl that rejects connection protocol messages (IDs >= 80) received before authentication is complete.
What it loads into context
Frontmatter
63 tokensAlways available to the agent
SKILL.md
732 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Overview
- Vulnerability Details
- The Fix
- Usage
- Key Technical Details
Scripts executed separately
scripts/patch_ssh_connection.pyscripts/run_patch.pyscripts/utils.py
Files
SKILL.mdcore3,114 bytesSKILL.mdcore3,114 bytesSKILL.mdcore3,114 bytesscripts/patch_ssh_connection.pyruns7,133 bytesscripts/run_patch.pyruns2,932 bytesscripts/utils.pyruns5,408 bytes
Read SKILL.md
# evo-erlang-ssh-cve-patch
## Overview
CVE-2025-32433 is a critical (CVSS 10.0) pre-authentication Remote Code Execution vulnerability in Erlang/OTP SSH server. The server fails to validate authentication state before processing SSH connection protocol messages (message IDs >= 80), allowing attackers to execute arbitrary commands without credentials.
## Vulnerability Details
- **Root Cause**: `ssh_connection.erl`'s `handle_msg/4` function processes channel messages (SSH_MSG_CHANNEL_OPEN, SSH_MSG_CHANNEL_REQUEST) without checking if `#ssh{authenticated}` is true
- **Attack Vector**: After completing key exchange, attacker sends SSH_MSG_CHANNEL_OPEN (ID 90) + SSH_MSG_CHANNEL_REQUEST (ID 98) with exec type, bypassing authentication entirely
- **Affected Versions**: All Erlang/OTP versions before 27.3.3, 26.2.5.11, 25.3.2.20
## The Fix
Add a pattern-matching clause in `ssh_connection.erl` that catches ANY message when `authenticated = false` on the server side, returning a disconnect error. This clause must be placed BEFORE any channel message handlers but is naturally placed after any disconnect handler.
### Exact Erlang Code to InsertView the complete source on GitHubevo-flink-session-job
When your agent uses it
Implement Flink jobs for Google Cluster Data analysis, specifically session-based analysis of task events. Handles parsing Google Cluster Data v2 CSV formats, session window computation on task SUBMIT events, and job completion filtering. Use for any task involving Flink + Google cluster trace data processing.
What it loads into context
Frontmatter
66 tokensAlways available to the agent
SKILL.md
852 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Overview
- Key Concepts
- Files
- Usage
- Build & Run
- Implementation Notes
- Troubleshooting
Scripts executed separately
scripts/generate_java.py
Files
SKILL.mdcore3,383 bytesSKILL.mdcore3,383 bytesSKILL.mdcore3,383 bytesSKILL.mdcore3,383 bytesscripts/generate_java.pyruns1,651 bytes
Read SKILL.md
# Flink Session Job for Google Cluster Data
## Overview
This skill implements a Flink job that processes Google Cluster Data v2 traces to find the longest stage (session of SUBMIT events) per finished job.
## Key Concepts
### Google Cluster Data v2 Schema
**Task Events CSV** (13 columns):
timestamp, missing_info, job_id, task_index, machine_id, event_type, user, scheduling_class, priority, cpu_request, memory_request, disk_request, different_machines_constraint
**Job Events CSV** (8 columns):View the complete source on GitHubevo-flood-risk-analysis
When your agent uses it
Detects flooding events at USGS streamgages by fetching instantaneous (15-min) gage height data, computing daily maximums, and comparing against NWS flood stage thresholds from the official NWS All Gauges Report. Outputs a CSV of stations with flood days.
What it loads into context
Frontmatter
63 tokensAlways available to the agent
SKILL.md
643 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Methodology
- Key Technical Rules
- Usage
- Output
Scripts executed separately
scripts/utils.py
Files
SKILL.mdcore2,527 bytesSKILL.mdcore2,527 bytesscripts/utils.pyruns9,224 bytes
Read SKILL.md
# evo-flood-risk-analysis
End-to-end pipeline for identifying flood days at USGS streamgages using gage height data and NWS flood stage thresholds.
## Methodology
1. **Gage height (parameter 00065)** is used — NOT discharge (00060).
2. **Daily maximum of instantaneous (15-min) readings** is the aggregation method. Use `nwis.get_iv()` to fetch instantaneous values, then resample to daily max with `.resample('D').max()`.
3. **NWS flood stage thresholds** come from the NWS All Gauges Report CSV at `https://water.noaa.gov/resources/downloads/reports/nwps_all_gauges_report.csv`. Match stations by USGS site ID (`usgs_id` or `gaugelid` column). The flood stage column is `sigstages.flood.stage` or similar.
4. **Flood condition**: `daily_max_gage_height >= flood_stage` (greater than or equal).
5. Only stations with a valid numeric NWS flood stage are evaluated.
6. Only stations with at least one flood day are included in output.
7. Sort output by `flood_days` descending.
View the complete source on GitHubevo-usgs-flood-detection
When your agent uses it
Detects flooding events at USGS streamgages by comparing daily streamflow against historical 90th percentile thresholds using the dataretrieval package. Use when analyzing flood occurrences over a date range for a list of USGS station IDs.
What it loads into context
Frontmatter
59 tokensAlways available to the agent
SKILL.md
719 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Overview
- Key Concepts
- Functions
- Usage
- Output Format
- Dependencies
Scripts executed separately
scripts/__init__.pyscripts/utils.py
Files
SKILL.mdcore2,866 bytesSKILL.mdcore2,866 bytesscripts/__init__.pyruns35 bytesscripts/utils.pyruns7,030 bytes
Read SKILL.md
# evo-usgs-flood-detection
## Overview
End-to-end pipeline for detecting flooding at USGS streamgages. Reads station IDs from a file, fetches daily streamflow values and historical statistics via `dataretrieval.nwis`, computes flood-day counts by comparing observed daily mean streamflow against the 90th percentile historical threshold for each calendar day, and writes filtered results to CSV.
## Key Concepts
### Flood Definition
A **flood day** is defined as a day where the observed daily mean streamflow (`00060_Mean`) exceeds the 90th percentile (`p90_va`) of historical daily mean streamflow for that same calendar day (month + day).
### Data Sources
- **Daily Values**: `nwis.get_dv(sites, parameterCd='00060', start, end)` → returns `(DataFrame, metadata)` tuple
- **Historical Stats**: `nwis.get_stats(sites, statReportType='daily', parameterCd='00060')` → returns `(DataFrame, metadata)` tuple with columns `month_nu`, `day_nu`, `p90_va`
View the complete source on GitHubevo-gh-data-fetcher
When your agent uses it
Fetches pull request and issue data from a GitHub repository using the GitHub REST API via curl/subprocess. Handles JSON output parsing, pagination, date range filtering, and error handling. Use when you need to retrieve structured PR or issue data from GitHub for analysis.
What it loads into context
Frontmatter
65 tokensAlways available to the agent
SKILL.md
714 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Key Concepts
- Usage
- Functions
- PR Data Structure (from /repos/{owner}/{repo}/pulls/{number})
- Issue Data Structure (from search API)
Scripts executed separately
scripts/fetch.pyscripts/utils.py
Files
SKILL.mdcore2,623 bytesSKILL.mdcore2,623 bytesscripts/fetch.pyruns5,081 bytesscripts/utils.pyruns4,269 bytes
Read SKILL.md
# evo-gh-data-fetcher
Fetches PR and issue data from GitHub repositories using the GitHub REST API (via curl subprocess calls). Works without gh CLI authentication by using unauthenticated API access for public repos.
## Key Concepts
- Uses GitHub Search API (`/search/issues`) with query qualifiers like `type:pr`, `type:issue`, `created:YYYY-MM-DD..YYYY-MM-DD`
- Search API returns max 1000 results per query; pagination handled automatically
- PR details (merge status, merged_at) require individual PR endpoint calls (`/repos/{owner}/{repo}/pulls/{number}`)
- Timestamps are ISO 8601 format with Z suffix (e.g., `2024-12-15T10:30:00Z`)
[Credential-related source omitted]
- PR states from API: `open`, `closed` with `merged` boolean and `merged_at` timestamp
- Issue labels are returned as array of objects: `[{"name": "bug", ...}]`
View the complete source on GitHubevo-gh-report-generator
When your agent uses it
Computes community pulse metrics from raw PR and issue data and writes a structured report.json file. Calculates PR counts by state, average time-to-merge, top contributor, bug issue counts, and resolved bugs. Use when you need to generate GitHub repository health metrics reports.
What it loads into context
Frontmatter
63 tokensAlways available to the agent
SKILL.md
496 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Key Concepts
- Usage
- Functions
- Output Format
Scripts executed separately
scripts/report.pyscripts/utils.py
Files
SKILL.mdcore2,027 bytesSKILL.mdcore2,027 bytesscripts/report.pyruns5,133 bytesscripts/utils.pyruns4,855 bytes
Read SKILL.md
# evo-gh-report-generator
Processes fetched PR/issue data to compute all required metrics and serialize results to report.json.
## Key Concepts
- PR states: REST API returns state as 'open'/'closed' with separate 'merged' boolean
- Time-to-merge: measured from created_at to merged_at in days, rounded to 1 decimal
- Top contributor: person who opened the most PRs (by user.login)
- Bug detection: any issue where at least one label name contains substring 'bug' (case-insensitive)
- Resolved bugs: bug issues where state == 'closed'
- closed PRs: PRs with state 'closed' that are NOT merged (merged == false)
## UsageView the complete source on GitHubevo-glm-simulation
When your agent uses it
Run the General Lake Model (GLM v3) for Lake Mendota — edit glm3.nml, execute the GLM binary, parse NetCDF output (depth = z_surface - z_layer), match to field observations, compute RMSE, and iteratively calibrate Kw, sw_factor, wind_factor, coef_mix_hyp to achieve RMSE < 2°C.
What it loads into context
Frontmatter
86 tokensAlways available to the agent
SKILL.md
839 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Directory contract
- Usage
- Key concepts
- Calibration levers (Mendota)
- Pitfalls
Scripts executed separately
scripts/utils.py
Files
SKILL.mdcore2,804 bytesSKILL.mdcore2,804 bytesscripts/utils.pyruns7,976 bytes
Read SKILL.md
# evo-glm-simulation
End-to-end workflow for running and calibrating GLM for Lake Mendota.
## Directory contract
- `/root/glm3.nml` — namelist (working dir is `/root/`)
- `/root/bcs/*.csv` — meteo, inflow (yahara, pheasant), outflow
- `/root/field_temp_oxy.csv` — field obs (columns: datetime, depth, temp, OXY_oxy)
- `/root/output/output.nc` — required output
## Usage
```python
import sysView the complete source on GitHubevo-gw-grid-search-output
When your agent uses it
Orchestrates mass parameter grid search across approximants for GW matched filtering, tracks best SNR per approximant, handles errors gracefully, manages memory, and writes final CSV output.
What it loads into context
Frontmatter
47 tokensAlways available to the agent
SKILL.md
535 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Functions
- Usage
- Key Design Decisions
Scripts executed separately
scripts/grid_utils.py
Files
SKILL.mdcore2,132 bytesSKILL.mdcore2,132 bytesscripts/grid_utils.pyruns3,141 bytes
Read SKILL.md
# evo-gw-grid-search-output
Orchestrates the grid search over mass parameters and approximants, using evo-gw-matched-filter-engine for core computations.
## Functions
### run_grid_search(gwf_path, channel, approximants, mass_range, conditioned_data=None, psd=None)
Runs matched filtering for every (m1, m2) combination where m1 >= m2 across all approximants.
Tracks best SNR per approximant. Handles TaylorT4 failures gracefully.
Returns list of dicts: [{approximant, snr, total_mass}, ...]
### extract_best_per_approximant(results)
Extracts the highest SNR entry per approximant from results list.
View the complete source on GitHubevo-gw-matched-filter-engine
When your agent uses it
Core utility for reading GWF frame files, conditioning gravitational wave detector data (highpass filtering, resampling, cropping, PSD estimation), generating waveform templates, and performing matched filtering to extract peak SNR values using PyCBC.
What it loads into context
Frontmatter
57 tokensAlways available to the agent
SKILL.md
681 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Functions
- Usage
- Key Parameters
Scripts executed separately
scripts/engine_utils.py
Files
SKILL.mdcore2,505 bytesSKILL.mdcore2,505 bytesscripts/engine_utils.pyruns5,136 bytes
Read SKILL.md
# evo-gw-matched-filter-engine
Core GW data processing and matched filtering engine for PyCBC-based gravitational wave detection.
## Functions
### read_and_condition_data(gwf_path, channel)
Reads a GWF frame file and conditions the data:
1. Read entire frame (no time bounds needed)
2. Highpass filter at 15 Hz
3. Crop 2s from both ends (FIR wraparound removal)
4. Resample to 2048 Hz
### estimate_psd(conditioned_data)View the complete source on GitHubevo-grid-dispatch-operator
When your agent uses it
End-to-end DC Optimal Power Flow with spinning reserve co-optimization. Parses MATPOWER JSON network data, builds DC power flow model with bus voltage angles, formulates and solves the DCOPF+reserve QP/LP via cvxpy (CLARABEL solver), computes line loading and operating margins, and produces a structured report.json.
What it loads into context
Frontmatter
81 tokensAlways available to the agent
SKILL.md
944 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Quick Start — Full Pipeline
- Formulation Details
- Module Reference
Scripts executed separately
scripts/data_loader.pyscripts/network_model.pyscripts/optimizer.pyscripts/report_generator.pyscripts/solve.py
Files
SKILL.mdcore3,306 bytesSKILL.mdcore3,306 bytesscripts/data_loader.pyruns1,862 bytesscripts/network_model.pyruns1,913 bytesscripts/optimizer.pyruns4,714 bytesscripts/report_generator.pyruns4,390 bytesscripts/solve.pyruns4,535 bytes
Read SKILL.md
# evo-grid-dispatch-operator
Solves DC Optimal Power Flow with spinning reserve co-optimization from MATPOWER JSON data and produces a structured dispatch report.
## Quick Start — Full Pipeline
```python
import subprocess, sys
subprocess.check_call([sys.executable, "-m", "pip", "install", "cvxpy", "clarabel", "-q"])
import sys as _sys
_sys.path.insert(0, '/app/environment/skills/evo-grid-dispatch-operator/scripts')
from solve import main
main("/root/network.json", "/root/report.json")View the complete source on GitHubevo-thermal-pid-control
When your agent uses it
PID controller tuning, discrete-time PID with anti-windup, closed-loop simulation, and control performance metrics. Uses SIMC tuning rules for first-order systems.
What it loads into context
Frontmatter
43 tokensAlways available to the agent
SKILL.md
519 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Functions
- Usage
- Key Domain Knowledge
Scripts executed separately
scripts/pid_utils.pyscripts/utils.py
Files
SKILL.mdcore1,849 bytesSKILL.mdcore1,849 bytesscripts/pid_utils.pyruns6,762 bytesscripts/utils.pyruns6,762 bytes
Read SKILL.md
# evo-thermal-pid-control
PID controller for HVAC thermal systems.
## Functions
- `calculate_simc_gains(K, tau, tau_c=None)` - SIMC PI gains; returns dict with Kp, Ki, Kd, lambda
- `DiscretePID(Kp, Ki, Kd, dt, output_min=0, output_max=100)` - PID class with anti-windup
- `run_closed_loop_control(sim, Kp, Ki, Kd, setpoint=22.0, duration=180.0)` - Run control loop
- `calculate_control_metrics(control_log)` - Compute rise_time, overshoot, settling_time, sse, max_temp
- `save_control_results(tuned_gains, control_log, metrics)` - Save JSON files to /root/
## Usage
View the complete source on GitHubevo-thermal-sysid
When your agent uses it
System identification utilities for first-order thermal systems. Runs open-loop step tests on HVAC simulator, collects calibration data, fits first-order exponential model, outputs estimated parameters (K, tau) with fit quality metrics.
What it loads into context
Frontmatter
52 tokensAlways available to the agent
SKILL.md
512 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Functions
- Usage
- Key Domain Knowledge
Scripts executed separately
scripts/sysid_utils.pyscripts/utils.py
Files
SKILL.mdcore1,880 bytesSKILL.mdcore1,880 bytesscripts/sysid_utils.pyruns5,157 bytesscripts/utils.pyruns5,157 bytes
Read SKILL.md
# evo-thermal-sysid
System identification for first-order thermal HVAC systems.
## Functions
- `run_calibration_test(sim, heater_power=50.0, duration=60.0)` - Run open-loop step test, returns calibration_log dict
- `first_order_step_response(t, K, tau, T_amb, U_step)` - First-order model: T_amb + K*U_step*(1-exp(-t/tau))
- `identify_system_params(calibration_log)` - Fit K and tau from calibration data using curve_fit
- `filter_temperature_data(temp_data, window_length=11, polyorder=2)` - Savitzky-Golay filter
- `calculate_fit_metrics(T_actual, T_predicted)` - Returns (r_squared, rmse)
- `save_calibration_results(calibration_log, estimated_params)` - Save JSON files to /root/
## UsageView the complete source on GitHubevo-invoice-fraud-detector
When your agent uses it
Implements fraud detection pipeline with fuzzy vendor matching via rapidfuzz, priority-ordered fraud checks, and JSON report generation.
What it loads into context
Frontmatter
36 tokensAlways available to the agent
SKILL.md
358 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Fraud Rules (Priority Order)
- Key Functions
- Usage
Scripts executed separately
scripts/utils.py
Files
SKILL.mdcore1,501 bytesSKILL.mdcore1,501 bytesscripts/utils.pyruns4,681 bytes
Read SKILL.md
# evo-invoice-fraud-detector
Detects invoice fraud using 5 priority-ordered rules.
## Fraud Rules (Priority Order)
1. Unknown Vendor - vendor name not in vendors database (fuzzy match score < 85)
2. IBAN Mismatch - vendor exists but IBAN doesn't match
3. Invalid PO - PO number doesn't exist in PO database
4. Amount Mismatch - PO exists but amount differs by > 0.01
5. Vendor Mismatch - PO valid but linked to different vendor ID
## Key Functions
- `find_vendor_match(vendor_name, vendor_dict)` - Fuzzy match using token_set_ratio, cutoff=85View the complete source on GitHubevo-pdf-invoice-parser
When your agent uses it
Extracts text from each page of a PDF invoice file using pdfplumber and parses structured fields (vendor name, IBAN, PO number, invoice amount) using regex.
What it loads into context
Frontmatter
46 tokensAlways available to the agent
SKILL.md
243 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Key Functions
- Usage
Scripts executed separately
scripts/utils.py
Files
SKILL.mdcore1,023 bytesSKILL.mdcore1,023 bytesscripts/utils.pyruns1,926 bytes
Read SKILL.md
# evo-pdf-invoice-parser
Extracts invoice data from PDF files. One invoice per page.
## Key Functions
- `extract_all_invoices(pdf_path)` - Returns list of dicts with page_number and parsed fields
- `extract_invoice_fields_from_text(text)` - Parse all fields from page text
- `extract_vendor_name(text)` - Extract vendor name after "From:"
- `extract_iban(text)` - Extract IBAN after "Payment IBAN:"
- `extract_invoice_amount(text)` - Extract total amount
- `extract_po_number(text)` - Extract PO number
## UsageView the complete source on GitHubevo-reference-data-loader
When your agent uses it
Loads and normalizes vendor master data from Excel and purchase order data from CSV into Python dictionaries for lookup operations.
What it loads into context
Frontmatter
31 tokensAlways available to the agent
SKILL.md
162 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Key Functions
- Usage
Scripts executed separately
scripts/utils.py
Files
SKILL.mdcore734 bytesSKILL.mdcore734 bytesscripts/utils.pyruns1,547 bytes
Read SKILL.md
# evo-reference-data-loader
Loads reference data for fraud detection.
## Key Functions
- `load_vendor_database(excel_path)` - Returns {vendor_id: {"name": name, "iban": iban}}
- `load_po_database(csv_path)` - Returns {po_number: {"vendor_id": vid, "amount": float}}
## Usage
```python
import sys
sys.path.insert(0, '/app/environment/skills/evo-reference-data-loader/scripts')View the complete source on GitHubevo-jax-compute
When your agent uses it
Implements all five JAX computation tasks - row-wise mean reduction, element-wise squaring, logistic loss gradient via jax.grad, RNN forward pass via jax.lax.scan, and JIT-compiled 2-layer MLP forward pass.
What it loads into context
Frontmatter
60 tokensAlways available to the agent
SKILL.md
735 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Quick Start
- Key Functions
- Domain Knowledge
Scripts executed separately
scripts/__init__.pyscripts/compute_utils.py
Files
SKILL.mdcore2,493 bytesSKILL.mdcore2,493 bytesscripts/__init__.pyruns170 bytesscripts/compute_utils.pyruns6,197 bytes
Read SKILL.md
# evo-jax-compute
All JAX computation logic for the five problem tasks, dispatching by problem ID.
## Quick Start
```python
import sys
sys.path.insert(0, '/app/environment/skills/evo-jax-compute/scripts')
from compute_utils import dispatch_task, compute_basic_reduce, compute_scan_rnn
# Dispatch by task ID
result = dispatch_task('basic_reduce', 'compute mean of each row', jax_data)
View the complete source on GitHubevo-jax-computing-basics
When your agent uses it
Complete utility for JAX numerical computation tasks - handles I/O (problem.json, .npy/.npz), and implements all five JAX computations (row-wise mean, element-wise square, logistic loss gradient, RNN scan, JIT MLP) with robust error handling and domain-aware edge case coverage.
What it loads into context
Frontmatter
76 tokensAlways available to the agent
SKILL.md
1,078 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Quick Start
- Key Functions
- Computation Details
- Important Notes
Scripts executed separately
scripts/compute_utils.pyscripts/io_utils.pyscripts/solve_tasks.py
Files
SKILL.mdcore3,718 bytesSKILL.mdcore3,718 bytesSKILL.mdcore3,718 bytesSKILL.mdcore3,718 bytesscripts/compute_utils.pyruns8,688 bytesscripts/io_utils.pyruns3,694 bytesscripts/solve_tasks.pyruns3,394 bytes
Read SKILL.md
# evo-jax-computing-basics
End-to-end skill for solving JAX computation tasks: parses problem.json, loads input data, dispatches to the correct JAX computation, and saves results as .npy files.
## Quick Start
```bash
# Run directly from the command line:
python /app/environment/skills/evo-jax-computing-basics/scripts/solve_tasks.py /app/problem.json
```
Or from Python:
```pythonView the complete source on GitHubevo-jax-io
When your agent uses it
Handles loading problem.json, reading .npy/.npz input files into JAX arrays, and saving JAX array results back to .npy files with proper numpy conversion.
What it loads into context
Frontmatter
46 tokensAlways available to the agent
SKILL.md
490 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Quick Start
- Key Functions
- Domain Knowledge
Scripts executed separately
scripts/__init__.pyscripts/io_utils.py
Files
SKILL.mdcore1,919 bytesSKILL.mdcore1,919 bytesscripts/__init__.pyruns73 bytesscripts/io_utils.pyruns2,430 bytes
Read SKILL.md
# evo-jax-io
All file I/O for JAX computation tasks: parsing problem.json, loading numpy/npz data files and converting to JAX arrays, and safely serializing JAX arrays to .npy output files.
## Quick Start
```python
import sys
sys.path.insert(0, '/app/environment/skills/evo-jax-io/scripts')
from io_utils import load_problem_json, load_input_data, save_jax_array
# Load task definitions
tasks = load_problem_json('/app/problem.json')
View the complete source on GitHubevo-ocr-preprocess-extract
When your agent uses it
Preprocesses receipt images and extracts text using Tesseract OCR with optimal settings for receipt layouts.
What it loads into context
Frontmatter
32 tokensAlways available to the agent
SKILL.md
335 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Key Functions
- Usage
- Pipeline
Scripts executed separately
scripts/utils.py
Files
SKILL.mdcore1,351 bytesSKILL.mdcore1,351 bytesscripts/utils.pyruns3,740 bytes
Read SKILL.md
# evo-ocr-preprocess-extract
Preprocesses receipt images using Pillow (grayscale, upscaling, contrast enhancement, binarization) and extracts raw text using pytesseract with optimal PSM configuration for receipt layouts.
## Key Functions
- `get_sorted_image_files(directory_path)` - Returns sorted list of (filename, full_path) tuples
- `preprocess_image(image_path, scale_factor=2, contrast_factor=2.0, threshold=140)` - Preprocesses image for OCR
- `extract_text_from_image(image_path, psm=4, oem=3, ...)` - Extracts text with preprocessing + Tesseract
- `extract_text_multi_config(image_path)` - Tries multiple configs for best result
## Usage
```pythonView the complete source on GitHubevo-receipt-parse-export
When your agent uses it
Parses OCR text from receipts to extract dates and total amounts using keyword-priority matching and regex, writes results to Excel.
What it loads into context
Frontmatter
36 tokensAlways available to the agent
SKILL.md
323 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Key Functions
- Usage
- Total Amount Priority Keywords
- Exclusion Keywords
Scripts executed separately
scripts/utils.py
Files
SKILL.mdcore1,323 bytesSKILL.mdcore1,323 bytesscripts/utils.pyruns5,666 bytes
Read SKILL.md
# evo-receipt-parse-export
Parses OCR text from receipts to extract dates and total amounts using prioritized keyword matching with exclusion rules, then writes structured results to Excel.
## Key Functions
- `extract_date(ocr_text)` - Extract date from OCR text, returns ISO format (YYYY-MM-DD) or None
- `extract_total_amount(ocr_text)` - Extract total amount using keyword priority, returns string with 2 decimals or None
- `parse_receipt_text(ocr_text)` - Returns dict with date and total_amount
- `write_results_to_excel(results, output_path)` - Write results to xlsx with sheet "results"
## Usage
```pythonView the complete source on GitHubevo-clinical-data-cleaning
When your agent uses it
Utility functions for cleaning raw clinical lab CSV data - handling decimal comma formats, scientific notation normalization, missing value detection, and numeric coercion of mixed-type columns.
What it loads into context
Frontmatter
44 tokensAlways available to the agent
SKILL.md
467 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Key Functions
- Usage
- Data Quality Issues Handled
Scripts executed separately
scripts/utils.py
Files
SKILL.mdcore1,988 bytesSKILL.mdcore1,988 bytesscripts/utils.pyruns2,901 bytes
Read SKILL.md
# evo-clinical-data-cleaning
Reusable utility functions for parsing and cleaning structural data quality issues in clinical lab CSV files.
## Key Functions
- `load_clinical_csv(filepath)` - Load CSV as strings to preserve formatting for manual cleaning
- `replace_decimal_commas(value)` - Convert European decimal commas to dots in a single value
- `replace_decimal_commas_df(df, skip_cols)` - Apply decimal comma fix to entire DataFrame
- `coerce_to_numeric(df, skip_cols)` - Convert all columns to float64, handling scientific notation
- `drop_incomplete_rows(df)` - Drop rows with any missing values
- `format_output_csv(df, output_filepath, skip_cols)` - Round to 2 decimal places, write CSV without scientific notation
## UsageView the complete source on GitHubevo-clinical-unit-harmonization
When your agent uses it
Domain-specific clinical lab unit detection and conversion module with conversion factor registry, physiological range boundaries, and boundary-based auto-detection logic to convert SI units to US conventional units.
What it loads into context
Frontmatter
47 tokensAlways available to the agent
SKILL.md
513 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Key Functions
- Usage
- Conversion Registry
Scripts executed separately
scripts/utils.py
Files
SKILL.mdcore1,726 bytesSKILL.mdcore1,726 bytesscripts/utils.pyruns3,096 bytes
Read SKILL.md
# evo-clinical-unit-harmonization
Converts clinical lab values from SI to US conventional units using boundary-based auto-detection.
## Key Functions
- `build_conversion_registry()` - Returns dict mapping column names to analyte configs
- `detect_and_convert_value(val, config)` - Detect and convert a single value
- `harmonize_column(series, config)` - Harmonize an entire column
- `harmonize_all_features(df, skip_cols)` - Harmonize all features in DataFrame
## Usage
```pythonView the complete source on GitHubevo-lake-data-pipeline
When your agent uses it
Loads, merges, and preprocesses lake water temperature and environmental driver CSV datasets. Provides category mapping for Heat/Flow/Wind/Human factor groups.
What it loads into context
Frontmatter
41 tokensAlways available to the agent
SKILL.md
489 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Category Mapping
- Usage
- Key Functions
- Import Pattern (avoiding naming conflicts)
Scripts executed separately
scripts/utils.py
Files
SKILL.mdcore2,109 bytesSKILL.mdcore2,109 bytesSKILL.mdcore2,109 bytesscripts/utils.pyruns1,931 bytes
Read SKILL.md
# evo-lake-data-pipeline
Loads and merges four CSV datasets (water_temperature, climate, land_cover, hydrology) into analysis-ready DataFrames.
## Category Mapping
| Category | Variables |
|----------|----------|
| Heat | AirTempLake, Shortwave, Longwave |
| Flow | Precip, Outflow, Inflow |
| Wind | WindSpeedLake |
| Human | DevelopedArea, AgricultureArea |
## UsageView the complete source on GitHubevo-lake-factor-attribution
When your agent uses it
Trains Random Forest to determine feature importances of environmental predictors on water temperature, maps features to categories (Heat/Flow/Wind/Human), and identifies the dominant driving factor category.
What it loads into context
Frontmatter
48 tokensAlways available to the agent
SKILL.md
606 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Category Mapping
- Usage
- Key Functions
- Output Format
- Import Pattern (avoiding naming conflicts)
Scripts executed separately
scripts/utils.py
Files
SKILL.mdcore2,780 bytesSKILL.mdcore2,780 bytesSKILL.mdcore2,780 bytesscripts/utils.pyruns3,444 bytes
Read SKILL.md
# evo-lake-factor-attribution
Uses Random Forest feature importances to attribute water temperature changes to physical driver categories.
## Category Mapping
| Category | Variables | Description |
|----------|-----------|-------------|
| Heat | AirTempLake, Shortwave, Longwave | Thermodynamic forcing |
| Flow | Precip, Outflow, Inflow | Hydrological forcing |
| Wind | WindSpeedLake | Mechanical forcing |
| Human | DevelopedArea, AgricultureArea | Anthropogenic forcing |
## UsageView the complete source on GitHubevo-lake-trend-analysis
When your agent uses it
Performs Mann-Kendall trend detection on lake water temperature time series using pymannkendall. Outputs slope (Sen's slope) and p-value to trend_result.csv.
What it loads into context
Frontmatter
45 tokensAlways available to the agent
SKILL.md
513 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Key Concepts
- Usage
- Key Functions
- Output Format
- Import Pattern (avoiding naming conflicts)
Scripts executed separately
scripts/utils.py
Files
SKILL.mdcore2,062 bytesSKILL.mdcore2,062 bytesSKILL.mdcore2,062 bytesscripts/utils.pyruns2,193 bytes
Read SKILL.md
# evo-lake-trend-analysis
Performs non-parametric Mann-Kendall trend detection on water temperature time series.
## Key Concepts
- Uses `pymannkendall` library for Mann-Kendall tests
- Sen's slope attribute: `result.slope`
- P-value attribute: `result.p`
- NaN values MUST be dropped before passing to pymannkendall
- For annual data (low autocorrelation risk), `original_test` is appropriate
- For data with autocorrelation, use `hamed_rao` or `yue_wang` methods
## UsageView the complete source on GitHubevo-latex-formula-extraction
When your agent uses it
Extracts display math formulas from marker-pdf Markdown output, strips equation numbers/tags/trailing punctuation, and organizes them for output.
What it loads into context
Frontmatter
39 tokensAlways available to the agent
SKILL.md
232 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Key Functions
- Usage
Scripts executed separately
scripts/utils.py
Files
SKILL.mdcore1,016 bytesSKILL.mdcore1,016 bytesscripts/utils.pyruns2,676 bytes
Read SKILL.md
# evo-latex-formula-extraction
Extracts display math formulas from marker-pdf Markdown output and cleans them.
## Key Functions
- `extract_display_formulas(markdown_text)` - Extract all $$...$$ blocks
- `strip_equation_numbering(formula)` - Remove \tag{}, \label{}, etc.
- `strip_trailing_punctuation(formula)` - Remove trailing commas, periods, etc.
- `normalize_formula(formula)` - Full cleanup pipeline
- `format_output(formulas, fixed_formulas)` - Format for markdown output
## Usage
View the complete source on GitHubevo-latex-syntax-validation
When your agent uses it
Validates extracted LaTeX formulas for syntax correctness and produces fixed versions of problematic formulas. Focuses on typos/syntax errors only.
What it loads into context
Frontmatter
39 tokensAlways available to the agent
SKILL.md
231 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Key Functions
- Usage
Scripts executed separately
scripts/utils.py
Files
SKILL.mdcore950 bytesSKILL.mdcore950 bytesscripts/utils.pyruns4,481 bytes
Read SKILL.md
# evo-latex-syntax-validation
Validates and fixes LaTeX formula syntax issues.
## Key Functions
- `validate_latex_formula(formula)` - Check for syntax issues
- `check_balanced_braces(formula)` - Check {} balance
- `check_balanced_brackets(formula)` - Check [] balance
- `fix_left_right_delimiters(formula)` - Balance \left/\right
- `fix_broken_commands(formula)` - Fix OCR typos in commands
- `detect_and_fix_all(formula)` - Full validation and fix pipeline
## UsageView the complete source on GitHubevo-pdf-to-markdown
When your agent uses it
Converts academic PDF to Markdown using marker-pdf v1.3.3, preserving LaTeX math delimiters in $$ format.
What it loads into context
Frontmatter
38 tokensAlways available to the agent
SKILL.md
261 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Key Functions
- Usage
- Notes
Scripts executed separately
scripts/utils.py
Files
SKILL.mdcore1,069 bytesSKILL.mdcore1,069 bytesscripts/utils.pyruns1,381 bytes
Read SKILL.md
# evo-pdf-to-markdown
Converts PDF files to Markdown text using the marker-pdf library (v1.3.3),
preserving LaTeX formulas in $$ delimiters.
## Key Functions
- `setup_marker_models()` - Initialize marker-pdf deep learning models
- `convert_pdf_to_markdown(pdf_path, force_ocr=False)` - Convert PDF to Markdown
## Usage
```python
import sysView the complete source on GitHubevo-lean4-recursive-sequence-inequality-proof
When your agent uses it
Provides utilities and guidance for constructing Lean 4 proofs involving recursive sequences and geometric sum inequalities. Covers reading existing Lean template files, crafting induction-based proofs with closed-form intermediate lemmas, and using math2001 textbook tactics (simple_induction, numbers, addarith, extra, rel) plus Mathlib4 tactics (norm_num, linarith, positivity, ring, field_simp) to handle arithmetic over rationals with powers of 2.
What it loads into context
Frontmatter
118 tokensAlways available to the agent
SKILL.md
1,213 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Overview
- Key Strategy: Closed-Form Lemma + Inequality
- Environment Details
- Proof Template
- Proof Approaches
- Usage
Scripts executed separately
scripts/utils.py
Files
SKILL.mdcore4,076 bytesSKILL.mdcore4,076 bytesscripts/utils.pyruns2,945 bytes
Read SKILL.md
# Lean 4 Recursive Sequence Inequality Proof Skill
## Overview
This skill solves problems of the form: given a recursively defined sequence
`S : ℕ → ℚ` (e.g., geometric partial sums), prove an inequality like `S n ≤ C`
for all natural numbers.
## Key Strategy: Closed-Form Lemma + Inequality
The recommended proof approach has two parts:
1. **Prove a closed-form lemma**: Show `S n = 2 - 1 / 2^n` by induction
2. **Derive the inequality**: Since `1/2^n ≥ 0`, we get `S n = 2 - 1/2^n ≤ 2`View the complete source on GitHubevo-defect-pipeline
When your agent uses it
End-to-end pipeline that reads test center log CSVs and product codebook files, orchestrates text normalization and fuzzy matching, and produces structured solution.json output.
What it loads into context
Frontmatter
42 tokensAlways available to the agent
SKILL.md
236 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Key Functions
- Usage
Scripts executed separately
scripts/utils.py
Files
SKILL.mdcore1,022 bytesSKILL.mdcore1,022 bytesscripts/utils.pyruns6,776 bytes
Read SKILL.md
# evo-defect-pipeline
Orchestration pipeline for defect text normalization.
## Key Functions
- `safe_read_csv(file_path)` - Read CSV with encoding fallbacks (utf-8, gbk, replace)
- `discover_codebooks(directory)` - Find codebook CSVs, map product_id to filepath
- `build_codebook_mapping(codebook_df)` - Build preprocessed label -> code dict
- `process_record(row, codebook_dict, standard_texts, threshold)` - Process single record
- `export_results_to_json(records, output_path)` - Write JSON with numpy-safe encoding
- `run_pipeline(data_dir, output_path, threshold)` - Full end-to-end pipeline
## UsageView the complete source on GitHubevo-fuzzy-match
When your agent uses it
Fuzzy string matching and confidence calibration for mapping normalized text segments against codebook entries. Implements SequenceMatcher, Levenshtein, Jaccard, cosine similarity, ensemble scoring, and UNKNOWN thresholding.
What it loads into context
Frontmatter
50 tokensAlways available to the agent
SKILL.md
311 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Key Functions
- Usage
Scripts executed separately
scripts/utils.py
Files
SKILL.mdcore1,115 bytesSKILL.mdcore1,115 bytesscripts/utils.pyruns4,924 bytes
Read SKILL.md
# evo-fuzzy-match
Fuzzy matching algorithms with calibrated confidence for manufacturing codebook matching.
## Key Functions
- `levenshtein_distance(s1, s2)` - Edit distance
- `levenshtein_ratio(s1, s2)` - Normalized 0-1 similarity
- `get_ngrams(text, n=2)` - Character n-grams
- `jaccard_similarity(s1, s2, n=2)` - Jaccard over n-gram sets
- `cosine_similarity(s1, s2, n=2)` - Cosine over n-gram vectors
- `ensemble_similarity(noisy, canonical)` - 0.6*SequenceMatcher + 0.4*cosine
- `calibrate_confidence(raw_score, threshold=0.55)` - Map to [0.5,1.0] or [0,0.49]
- `match_segment(clean_text, codebook, standard_texts, threshold=0.55)` - Match against codebookView the complete source on GitHubevo-text-normalize
When your agent uses it
Preprocesses and normalizes noisy multilingual (Chinese-English mixed) industrial text. Handles full-width to half-width conversion, Unicode NFKC normalization, lowercasing, whitespace cleanup, punctuation normalization, abbreviation expansion, and splitting compound reasons.
What it loads into context
Frontmatter
57 tokensAlways available to the agent
SKILL.md
254 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Key Functions
- Usage
Scripts executed separately
scripts/utils.py
Files
SKILL.mdcore1,191 bytesSKILL.mdcore1,191 bytesscripts/utils.pyruns2,853 bytes
Read SKILL.md
# evo-text-normalize
Text preprocessing for noisy manufacturing defect logs with mixed Chinese-English content.
## Key Functions
- `normalize_width(text)` - NFKC normalization + Chinese punctuation mapping
- `preprocess_text(text)` - Full pipeline: width norm, lowercase, whitespace, abbreviations
- `expand_abbreviations(text)` - Expand common manufacturing abbreviations
- `split_mixed_text(text)` - Split mixed Chinese/English into contiguous blocks
- `split_compound_reasons(raw_text)` - Split compound reasons by delimiters, preserving spans
## Usage
View the complete source on GitHubevo-reflow-handbook-parser
When your agent uses it
Extracts reflow soldering process parameters from the PDF handbook including preheat range, ramp rate limits, TAL window, peak temp requirements, and conveyor speed formulas.
What it loads into context
Frontmatter
44 tokensAlways available to the agent
SKILL.md
373 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Purpose
- Key Parameters (from handbook)
- Usage
Scripts executed separately
scripts/utils.py
Files
SKILL.mdcore1,552 bytesSKILL.mdcore1,552 bytesscripts/utils.pyruns2,279 bytes
Read SKILL.md
# evo-reflow-handbook-parser
## Purpose
Parse the reflow machine handbook PDF and return structured dictionaries of all process thresholds, formulas, and compliance limits.
## Key Parameters (from handbook)
### Preheat Zone
- Temperature range: 100°C to 150°C
- Max ramp rate: 2°C/second
- Ramp rate equation: ΔT/Δt (temperature change over time change)
### TAL (Wetting Time)
- Window: 30 to 60 secondsView the complete source on GitHubevo-reflow-json-output
When your agent uses it
Formats and serializes computed analysis results into exact JSON structures for q01-q05 output files with numpy/pandas type coercion, rounding, and sorting.
What it loads into context
Frontmatter
41 tokensAlways available to the agent
SKILL.md
237 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Purpose
- Key Functions
- Usage
Scripts executed separately
scripts/utils.py
Files
SKILL.mdcore927 bytesSKILL.mdcore927 bytesscripts/utils.pyruns3,516 bytes
Read SKILL.md
# evo-reflow-json-output
## Purpose
JSON serialization with proper type handling for manufacturing data.
## Key Functions
- `safe_json_dump(data, filepath)` - Write JSON with numpy type handling
- `build_q01_output(max_ramp_by_run, ramp_rate_limit)` - Format Q1
- `build_q02_output(tal_results)` - Format Q2
- `build_q03_output(failing_runs, min_peak_by_run)` - Format Q3
- `build_q04_output(speed_results)` - Format Q4
- `build_q05_output(best_runs)` - Format Q5
## UsageView the complete source on GitHubevo-reflow-thermal-analysis
When your agent uses it
Processes thermocouple CSV data, MES logs, and test defect data to compute preheat ramp rates, TAL, peak temperatures, conveyor speed compliance, and best-run selection per board family.
What it loads into context
Frontmatter
49 tokensAlways available to the agent
SKILL.md
338 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Purpose
- Key Functions
- Usage
Scripts executed separately
scripts/utils.py
Files
SKILL.mdcore1,262 bytesSKILL.mdcore1,262 bytesscripts/utils.pyruns8,878 bytes
Read SKILL.md
# evo-reflow-thermal-analysis
## Purpose
All CSV data loading, merging, time-series computation, and compliance checks.
## Key Functions
- `load_thermocouple_data()` - Load TC CSV
- `load_mes_log()` - Load MES CSV
- `load_test_defects()` - Load defects CSV
- `calculate_ramp_rates(tc_df)` - Compute dT/dt per interval
- `get_max_preheat_ramp_by_run(tc_df, preheat_max_c=150.0)` - Max ramp in preheat zone using largest_mass TC
- `calculate_tal_by_run(tc_df, mes_df)` - TAL using largest_mass TC and per-run liquidus
- `check_peak_temp_compliance(tc_df, mes_df, peak_margin_c=20.0)` - Peak temp check
- `check_conveyor_speed_compliance(mes_df)` - Min speed feasibilityView the complete source on GitHubevo-fjsp-data-io
When your agent uses it
Parses FJSP instance, downtime, policy, baseline files and exports solutions to JSON/CSV.
What it loads into context
Frontmatter
31 tokensAlways available to the agent
SKILL.md
215 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Usage
- Functions
Scripts executed separately
scripts/utils.py
Files
SKILL.mdcore839 bytesSKILL.mdcore839 bytesscripts/utils.pyruns2,807 bytes
Read SKILL.md
# evo-fjsp-data-io
All file I/O for FJSP scheduling tasks.
## Usage
```python
import sys
sys.path.insert(0, '/app/environment/skills/evo-fjsp-data-io/scripts')
from utils import (parse_fjsp_instance, parse_downtimes_csv,
parse_policy_budgets, parse_baseline_schedule,
export_solution_json, export_solution_csv)
```
## Functions
- `parse_fjsp_instance(filepath)` -> (jobs, num_machines)View the complete source on GitHubevo-fjsp-scheduler
When your agent uses it
Core FJSP scheduling engine with downtime-aware scheduling, greedy dispatching, repair, and SA optimization.
What it loads into context
Frontmatter
31 tokensAlways available to the agent
SKILL.md
104 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Usage
Scripts executed separately
scripts/utils.py
Files
SKILL.mdcore433 bytesSKILL.mdcore433 bytesscripts/utils.pyruns11,098 bytes
Read SKILL.md
# evo-fjsp-scheduler
## Usage
```python
import sys
sys.path.insert(0, '/app/environment/skills/evo-fjsp-scheduler/scripts')
from utils import (find_earliest_start, greedy_dispatching, repair_schedule,
decode_schedule, simulated_annealing_fjsp, validate_policy_budgets)
```View the complete source on GitHubevo-fjsp-validator
When your agent uses it
Validates FJSP schedules for completeness, precedence, machine overlaps, downtime overlaps, eligibility.
What it loads into context
Frontmatter
28 tokensAlways available to the agent
SKILL.md
101 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Usage
Scripts executed separately
scripts/utils.py
Files
SKILL.mdcore441 bytesSKILL.mdcore441 bytesscripts/utils.pyruns2,628 bytes
Read SKILL.md
# evo-fjsp-validator
## Usage
```python
import sys
sys.path.insert(0, '/app/environment/skills/evo-fjsp-validator/scripts')
from utils import (validate_schedule, check_precedence, check_machine_overlaps,
check_downtime_overlaps, check_eligibility_and_duration, calculate_makespan)
```View the complete source on GitHubevo-template-matching-counter
When your agent uses it
Counts occurrences of template objects (coins, enemies, turtles) in grayscale keyframe images using OpenCV matchTemplate with TM_CCOEFF_NORMED and Non-Maximum Suppression, then aggregates results into a CSV file.
What it loads into context
Frontmatter
55 tokensAlways available to the agent
SKILL.md
632 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Overview
- Key Concepts
- Functions
- Usage
- Depends On
Scripts executed separately
scripts/counter_utils.py
Files
SKILL.mdcore2,582 bytesSKILL.mdcore2,582 bytesscripts/counter_utils.pyruns5,709 bytes
Read SKILL.md
# evo-template-matching-counter
## Overview
Counts game sprites (coins, enemies, turtles) in grayscale keyframe images using OpenCV template matching with NMS deduplication, outputs results to CSV.
## Key Concepts
- Uses `cv2.TM_CCOEFF_NORMED` - normalized correlation coefficient, best for rigid 2D pixel art
- Default threshold: 0.8 (optimal for Super Mario sprites with MP4 compression artifacts)
- Non-Maximum Suppression (NMS) with IoU overlap threshold of 0.3 to deduplicate detections
- Both frame and template MUST be grayscale (single channel) for matching
- `np.where(result >= threshold)` returns (y_coords, x_coords) - row/column order
- Template must be smaller than frame in both dimensions
- CSV output columns: frame_id (full path like /root/keyframes_001.png), coins, enemies, turtles
View the complete source on GitHubevo-video-keyframe-extraction
When your agent uses it
Extracts keyframes from an MP4 video at uniform temporal intervals using OpenCV VideoCapture, saves them with sequential naming (keyframes_001.png, keyframes_002.png, etc.), and converts them in-place from BGR to grayscale.
What it loads into context
Frontmatter
61 tokensAlways available to the agent
SKILL.md
564 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Overview
- Key Concepts
- Functions
- Usage
Scripts executed separately
scripts/video_utils.py
Files
SKILL.mdcore2,298 bytesSKILL.mdcore2,298 bytesscripts/video_utils.pyruns3,111 bytes
Read SKILL.md
# evo-video-keyframe-extraction
## Overview
Extracts keyframes from gameplay video using uniform temporal sampling, saves with zero-padded sequential naming, and converts to grayscale in-place.
## Key Concepts
- Uses `cv2.VideoCapture` for video decoding with embedded FFmpeg backend
- Uniform temporal sampling: extract 1 frame per second (frame_interval = int(fps * 1.0))
- Frames saved as PNG with `cv2.imwrite()` using zero-padded naming: `keyframes_001.png`, `keyframes_002.png`, etc.
- Grayscale conversion done in-place: read with `cv2.IMREAD_GRAYSCALE`, overwrite original file
- OpenCV uses BGR channel order (not RGB)
- For a 27-second 60fps video, extracts 27 keyframes (one per second)
## FunctionsView the complete source on GitHubevo-mars-clustering-eval
When your agent uses it
Core clustering and evaluation utilities for Mars cloud annotations. Custom weighted Euclidean DBSCAN clustering, centroid computation, greedy bipartite matching, and per-image F1/delta scoring.
What it loads into context
Frontmatter
48 tokensAlways available to the agent
SKILL.md
390 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Key Functions
- Usage
- Domain Rules
Scripts executed separately
scripts/utils.py
Files
SKILL.mdcore1,510 bytesSKILL.mdcore1,510 bytesscripts/utils.pyruns5,051 bytes
Read SKILL.md
# evo-mars-clustering-eval
Core clustering and evaluation utilities for DBSCAN-based Mars cloud annotation clustering.
## Key Functions
- `weighted_euclidean_pairwise(u, v, w)` - Custom distance: sqrt((w*dx)^2 + ((2-w)*dy)^2)
- `compute_precomputed_distance_matrix(X, w)` - Build precomputed distance matrix for DBSCAN
- `run_dbscan_and_get_centroids(X, eps, min_samples, dist_matrix)` - Run DBSCAN, return centroids
- `greedy_match(centroids, ground_truth, threshold=100.0)` - Greedy bipartite matching
- `score_image(citsci_points, expert_points, eps, min_samples, w)` - Full per-image scoring
## Usage
View the complete source on GitHubevo-mars-grid-search
When your agent uses it
Parallel grid search over DBSCAN hyperparameters for Mars cloud clustering. Aggregates per-image F1 and delta scores with proper averaging semantics.
What it loads into context
Frontmatter
37 tokensAlways available to the agent
SKILL.md
313 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Key Functions
- Usage
- Averaging Rules
Scripts executed separately
scripts/utils.py
Files
SKILL.mdcore1,190 bytesSKILL.mdcore1,190 bytesscripts/utils.pyruns3,197 bytes
Read SKILL.md
# evo-mars-grid-search
Parallel grid search over DBSCAN hyperparameters.
## Key Functions
- `load_data(citsci_path, expert_path)` - Load CSVs, return grouped dicts
- `evaluate_hyperparameter_combo(ms, eps, sw, images, citsci_dict, expert_dict)` - Eval one combo
- `run_grid_search(unique_images, citsci_dict, expert_dict, n_jobs)` - Full parallel grid search
- `filter_results(results_df, min_f1=0.5)` - Filter to F1 > 0.5
## Usage
```pythonView the complete source on GitHubevo-mars-pareto-output
When your agent uses it
Computes Pareto frontier from grid search results (maximize F1, minimize delta) and writes formatted CSV output.
What it loads into context
Frontmatter
34 tokensAlways available to the agent
SKILL.md
251 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Key Functions
- Usage
- Output Format
Scripts executed separately
scripts/utils.py
Files
SKILL.mdcore953 bytesSKILL.mdcore953 bytesscripts/utils.pyruns1,350 bytes
Read SKILL.md
# evo-mars-pareto-output
Pareto frontier computation and formatted CSV output.
## Key Functions
- `compute_pareto_frontier(results_df)` - Find Pareto-optimal points (max F1, min delta)
- `format_and_save_pareto_csv(pareto_df, output_path)` - Format and save to CSV
## Usage
```python
import sys
sys.path.insert(0, '/app/environment/skills/evo-mars-pareto-output/scripts')View the complete source on GitHubevo-dubbing-audio-processing
When your agent uses it
Handles audio resampling, loudness normalization per ITU-R BS.1770-4, and LUFS measurement for TTS segments to ensure broadcast-quality output.
What it loads into context
Frontmatter
44 tokensAlways available to the agent
SKILL.md
353 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Key Functions
- Usage
- Technical Details
Scripts executed separately
scripts/utils.py
Files
SKILL.mdcore1,322 bytesSKILL.mdcore1,322 bytesscripts/utils.pyruns2,964 bytes
Read SKILL.md
# evo-dubbing-audio-processing
Resamples audio from Kokoro's 24kHz to 48kHz and applies ITU-R BS.1770-4 loudness normalization.
## Key Functions
- `resample_audio(audio, orig_sr, target_sr)` - Resample numpy array
- `measure_lufs(audio_path)` - Measure LUFS using FFmpeg loudnorm filter (pass 1)
- `normalize_loudness(audio_path, output_path, target_lufs)` - Two-pass loudness normalization
- `process_segment_audio(input_path, output_path, target_sr, target_lufs)` - Full processing pipeline
## Usage
```pythonView the complete source on GitHubevo-dubbing-mux-report
When your agent uses it
Muxes normalized TTS audio segments into the original video at precise time offsets using FFmpeg, and generates the JSON report with timing, drift, and loudness metadata.
What it loads into context
Frontmatter
46 tokensAlways available to the agent
SKILL.md
207 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Key Functions
- Usage
Scripts executed separately
scripts/utils.py
Files
SKILL.mdcore867 bytesSKILL.mdcore867 bytesscripts/utils.pyruns3,558 bytes
Read SKILL.md
# evo-dubbing-mux-report
Muxes dubbed audio into video and generates JSON report.
## Key Functions
- `get_video_duration(path)` - Get video duration using ffprobe
- `build_ffmpeg_mux_command(video, segments, output)` - Build FFmpeg command
- `mux_dubbed_video(video, segments, output)` - Execute muxing
- `calculate_drift(placed_start, tts_duration, window_end)` - Calculate timing drift
- `generate_report_json(data, output_path)` - Write JSON report
## Usage
View the complete source on GitHubevo-dubbing-tts-synthesis
When your agent uses it
Synthesizes target-language speech from text using Kokoro TTS, with speed/duration control to fit precise time windows. Handles SRT parsing, text extraction, and produces WAV segments.
What it loads into context
Frontmatter
50 tokensAlways available to the agent
SKILL.md
407 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Key Functions
- Usage
- Technical Details
Scripts executed separately
scripts/utils.py
Files
SKILL.mdcore1,596 bytesSKILL.mdcore1,596 bytesscripts/utils.pyruns5,445 bytes
Read SKILL.md
# evo-dubbing-tts-synthesis
Synthesizes target-language TTS audio fitted to SRT time windows using Kokoro.
## Key Functions
- `parse_srt_file(path)` - Parse SRT file, return list of dicts with index, text, start_sec, end_sec, duration_sec
- `read_target_language(path)` - Read target language code from file
- `synthesize_segment(text, lang_code, voice, speed)` - Generate audio array using Kokoro
- `fit_audio_to_window(text, lang_code, voice, target_duration)` - Synthesize and adjust speed to fit window
- `generate_tts_segments(segments_srt, source_srt, target_srt, lang_code, output_dir)` - Full pipeline
## Usage
View the complete source on GitHubevo-docx-template-filler
When your agent uses it
A utility module for filling Word document templates (.docx) with data from JSON files. Handles split-run-aware text replacement to preserve formatting, traverses all document containers (body, tables, nested tables, headers, footers, text boxes), and processes conditional IF/END_IF blocks by keeping or removing content based on data values.
What it loads into context
Frontmatter
85 tokensAlways available to the agent
SKILL.md
680 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Key Capabilities
- Usage
- Functions
- Conditional Logic
Scripts executed separately
scripts/utils.py
Files
SKILL.mdcore2,851 bytesSKILL.mdcore2,851 bytesscripts/utils.pyruns9,654 bytes
Read SKILL.md
# evo-docx-template-filler
Fill Word (.docx) templates with data from JSON, preserving formatting and handling conditionals.
## Key Capabilities
1. **Split-run-aware replacement**: Handles OOXML split runs where placeholders like `{{NAME}}` are fragmented across multiple XML runs
2. **Comprehensive container traversal**: Body paragraphs, tables (nested), headers (default/first/even), footers, text boxes
3. **Conditional blocks**: `{{IF_KEY}}...{{END_IF_KEY}}` - keeps content when condition is true (removes markers), removes entire block when false
4. **Format preservation**: Replaces text at run level, never overwrites paragraph.text
5. **Safe deletion**: Prevents OOXML corruption by not removing the last paragraph in table cells
## Usage
View the complete source on GitHubevo-document-classify-and-sort
When your agent uses it
Classifies document text into 5 categories (LLM, trapped_ion_and_qc, black_hole, DNA, music_history) using weighted keyword matching, then moves files into folders.
What it loads into context
Frontmatter
50 tokensAlways available to the agent
SKILL.md
235 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Usage
- Key Functions
Scripts executed separately
scripts/utils.py
Files
SKILL.mdcore1,017 bytesSKILL.mdcore1,017 bytesscripts/utils.pyruns7,128 bytes
Read SKILL.md
# evo-document-classify-and-sort
## Usage
```python
import sys
sys.path.insert(0, '/app/environment/skills/evo-document-classify-and-sort/scripts')
sys.path.insert(0, '/app/environment/skills/evo-document-text-extraction/scripts')
from utils import extract_text
import importlib
classify_mod = importlib.import_module('utils')
# Better approach:
sys.path.insert(0, '/app/environment/skills/evo-document-classify-and-sort/scripts')
from utils import classify_document, create_category_folders, sort_files_into_folders
```
View the complete source on GitHubevo-document-text-extraction
When your agent uses it
Extracts text from PDF, DOCX, and PPTX files using PyPDF2, pdfplumber, pdftotext CLI, and stdlib zipfile+XML fallbacks.
What it loads into context
Frontmatter
48 tokensAlways available to the agent
SKILL.md
246 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Usage
- Key Functions
Scripts executed separately
scripts/utils.py
Files
SKILL.mdcore889 bytesSKILL.mdcore889 bytesscripts/utils.pyruns3,176 bytes
Read SKILL.md
# evo-document-text-extraction
## Usage
```python
import sys
sys.path.insert(0, '/app/environment/skills/evo-document-text-extraction/scripts')
from utils import extract_text, extract_text_pdf, extract_text_docx, extract_text_pptx
text = extract_text('/path/to/file.pdf') # auto-detects format
```
## Key Functions
- `extract_text(filepath, max_pages=3)` - unified interface, auto-detects by extension
- `extract_text_pdf(filepath, max_pages=3)` - PDF with fallback chain: PyPDF2 -> pdftotext -> pdfplumber
- `extract_text_docx(filepath)` - DOCX via zipfile+XML stdlibView the complete source on GitHubevo-pdf-content-extraction
When your agent uses it
Extracts and analyzes text content from PDF pages to identify author-revealing information including names, affiliations, emails, arXiv IDs, venue/conference mentions, and other identity-leaking content.
What it loads into context
Frontmatter
51 tokensAlways available to the agent
SKILL.md
318 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Key Functions
- Usage
Scripts executed separately
scripts/extraction.py
Files
SKILL.mdcore1,425 bytesSKILL.mdcore1,425 bytesscripts/extraction.pyruns8,474 bytes
Read SKILL.md
# evo-pdf-content-extraction
Extracts text from academic PDFs and identifies all content that could reveal authorship for anonymization purposes.
## Key Functions
- `extract_page_text(page)` - Get plain text from a page
- `extract_words_with_positions(page)` - Get words with bounding box coordinates
- `identify_author_block_region(page)` - Find the author block area on first page
- `detect_arxiv_identifiers(text)` - Find arXiv IDs in text
- `detect_email_addresses(text)` - Find email addresses
- `detect_affiliations(text)` - Find institutional affiliations
- `detect_venue_statements(text)` - Find venue/conference acceptance statements
- `get_all_redaction_targets(pdf_path)` - Main function: analyze a PDF and return all strings to redactView the complete source on GitHubevo-pdf-redaction-engine
When your agent uses it
Performs physical redaction of identified content in PDF documents using PyMuPDF's redaction API. Handles exact string redaction, regex-based redaction, hyperlink removal, metadata scrubbing, and secure document saving.
What it loads into context
Frontmatter
53 tokensAlways available to the agent
SKILL.md
352 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Key Functions
- Usage
Scripts executed separately
scripts/redaction.py
Files
SKILL.mdcore1,478 bytesSKILL.mdcore1,478 bytesscripts/redaction.pyruns3,303 bytes
Read SKILL.md
# evo-pdf-redaction-engine
Performs physical PDF redaction using PyMuPDF (fitz). Applies redaction annotations, removes hyperlinks, purges metadata, and saves securely with garbage collection.
## Key Functions
- `redact_exact_strings(page, strings)` - Add redaction annotations for exact string matches
- `redact_regex_patterns(page, patterns)` - Add redaction annotations for regex matches
- `redact_page_region(page, rect)` - Redact an entire rectangular region
- `scrub_hyperlinks(page, link_patterns)` - Remove identifying hyperlinks and redact their text
- `scrub_metadata(doc)` - Purge standard and XMP metadata
- `anonymize_pdf(input_path, output_path, exact_strings, regex_patterns, link_patterns)` - Full pipeline
- `save_redacted_document(doc, output_path)` - Save with garbage=4 and deflate=True
View the complete source on GitHubevo-parallel-batch-search
When your agent uses it
Provides utilities for parallelizing batch query search over a pre-built TF-IDF index using the worker initializer pattern to efficiently share the read-only index across worker processes.
What it loads into context
Frontmatter
43 tokensAlways available to the agent
SKILL.md
281 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Overview
- Worker Initializer Pattern
- Usage
- Functions
Scripts executed separately
scripts/utils.py
Files
SKILL.mdcore1,292 bytesSKILL.mdcore1,292 bytesscripts/utils.pyruns6,988 bytes
Read SKILL.md
# Parallel Batch Search
## Overview
Parallelizes batch query search using ProcessPoolExecutor with the
worker initializer pattern. The index is passed once per worker at
pool creation time (via initargs), avoiding repeated pickling.
## Worker Initializer Pattern
- `init_search_worker(index, documents, top_k)` sets module-level globals
- `worker_search_query(query)` reads those globals to perform search
- Each query is independent - perfect for data parallelism
## Usage
```pythonView the complete source on GitHubevo-parallel-determinism
When your agent uses it
Provides patterns and utilities to ensure parallel TF-IDF results are identical to the sequential baseline, addressing floating-point ordering, tie-breaking, and pickling compatibility.
What it loads into context
Frontmatter
42 tokensAlways available to the agent
SKILL.md
276 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Overview
- Key Principles
- Usage
- Functions
Scripts executed separately
scripts/utils.py
Files
SKILL.mdcore1,270 bytesSKILL.mdcore1,270 bytesscripts/utils.pyruns2,811 bytes
Read SKILL.md
# Parallel Determinism
## Overview
Ensures parallel results match sequential exactly by handling:
- Floating-point accumulation order
- Tie-breaking in result sorting
- Pickling compatibility for multiprocessing
- Safe context selection (fork vs spawn)
## Key Principles
1. **FP Ordering**: Iterate query terms in same order as sequential (dict insertion order)
2. **Tie-breaking**: Sort by (-score, doc_id) for deterministic ordering
3. **Pickling**: Define NamedTuples/dataclasses at module level
4. **Context**: Use 'fork' on Linux for performance (copy-on-write)View the complete source on GitHubevo-parallel-index-building
When your agent uses it
Provides utilities for parallelizing TF-IDF inverted index construction using a MapReduce approach - chunking documents, computing local TF and DF in worker processes, merging partial results, and finalizing TF-IDF scores with global DF.
What it loads into context
Frontmatter
55 tokensAlways available to the agent
SKILL.md
429 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Overview
- Key Formulas (matching sequential.py)
- Usage
- Functions
Scripts executed separately
scripts/utils.py
Files
SKILL.mdcore1,720 bytesSKILL.mdcore1,720 bytesscripts/utils.pyruns8,964 bytes
Read SKILL.md
# Parallel TF-IDF Index Building
## Overview
Parallelizes TF-IDF index construction using MapReduce:
1. **Chunk**: Split documents into chunks
2. **Map**: Workers compute local TF and DF per chunk
3. **Reduce**: Merge partial results (Counter.update for DF, dict.update for TF)
4. **Finalize**: Compute IDF and TF-IDF scores, build inverted index
## Key Formulas (matching sequential.py)
- TF(t,d) = count(t in d) / total_tokens(d)
- IDF(t) = log(N / df(t)) + 1
- TF-IDF = TF * IDF
- Posting lists sorted by score descendingView the complete source on GitHubevo-tpp-solver
When your agent uses it
Solve TPP (Travelling Purchase Problem) PDDL planning tasks. Use when you need to read a problem.json config file, parse PDDL domain/problem files, generate valid plans using pyperplan via unified_planning, format actions as function-call strings, write plan output files, and serialize plans as pickle. Handles the complete pipeline from JSON config to validated plan output.
What it loads into context
Frontmatter
85 tokensAlways available to the agent
SKILL.md
1,057 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- When to use this skill
- Quick Start
- Pipeline Overview
- Key Implementation Details
- Script Reference
Scripts executed separately
scripts/__init__.pyscripts/solve.py
Files
SKILL.mdcore3,924 bytesSKILL.mdcore3,924 bytesSKILL.mdcore3,924 bytesscripts/__init__.pyruns25 bytesscripts/solve.pyruns8,294 bytes
Read SKILL.md
# TPP PDDL Solver
Solves Travelling Purchase Problem (TPP) planning tasks encoded in PDDL using pyperplan via the unified_planning framework.
## When to use this skill
- You have a `problem.json` file listing TPP planning tasks
- Each task specifies a PDDL domain file, problem file, and output path
- You need to generate valid plans and write them as formatted text files
- You need pickle-serialized plans for validation compatibility
## Quick Start
Run the solver script directly:View the complete source on GitHubevo-dataframe-diff-report
When your agent uses it
Compares two pandas DataFrames (old vs new) by a key column to identify deleted rows and modified fields, then exports results as a properly formatted JSON report with NumPy-safe serialization.
What it loads into context
Frontmatter
49 tokensAlways available to the agent
SKILL.md
462 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Key Functions
- Value Type Rules
- Usage
- Dependencies
Scripts executed separately
scripts/utils.py
Files
SKILL.mdcore1,926 bytesSKILL.mdcore1,926 bytesscripts/utils.pyruns7,642 bytes
Read SKILL.md
# evo-dataframe-diff-report
Compares old vs new DataFrames to find deletions and modifications, exports as JSON.
## Key Functions
### find_deleted_employees(df_old, df_new, id_column='ID')
Finds IDs in old but not in new. Returns sorted list of ID strings.
### find_modified_employees(df_old, df_new, id_column='ID', numeric_columns=None, float_tolerance=1e-4)
Finds field-level changes for employees in both DataFrames.
Returns list of dicts: {"id": "EMP00003", "field": "Salary", "old_value": 50020, "new_value": 55010}
Sorted by (id, field).
View the complete source on GitHubevo-pdf-excel-extraction
When your agent uses it
Extracts tabular data from PDF files using pdfplumber and reads Excel files using pandas/openpyxl, returning normalized pandas DataFrames with proper data types.
What it loads into context
Frontmatter
44 tokensAlways available to the agent
SKILL.md
478 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Key Functions
- Usage
- Domain Knowledge
Scripts executed separately
scripts/utils.py
Files
SKILL.mdcore2,011 bytesSKILL.mdcore2,011 bytesscripts/utils.pyruns5,398 bytes
Read SKILL.md
# evo-pdf-excel-extraction
Extracts tabular data from PDF files and Excel files, returning normalized DataFrames.
## Key Functions
### extract_table_from_pdf(pdf_path, table_settings=None)
Extracts a multi-page table from a PDF. Handles:
- Multi-page concatenation (iterates all pages)
- Header detection from first page
- Repeated header detection on subsequent pages
- Cell cleaning (whitespace, newlines)
### read_excel_file(excel_path, id_column='ID', sheet_name=0, dtype_map=None)View the complete source on GitHubevo-pedestrian-vlm-counting
When your agent uses it
Count unique pedestrians in surveillance video frames using Vision LLM APIs (OpenAI GPT-4o or Google Gemini) and write results to Excel. Use when you need to analyze surveillance footage for pedestrian counting, perform person re-identification across video frames, or generate Excel reports of pedestrian counts per video file. Supports both OpenAI and Gemini vision APIs with robust response parsing.
What it loads into context
Frontmatter
87 tokensAlways available to the agent
SKILL.md
813 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- When to Use
- Dependencies
- Core Functions
- Usage Example
- Prompt Engineering Strategy
- Excel Output Format
Scripts executed separately
scripts/pedestrian_counting.py
Files
SKILL.mdcore3,677 bytesSKILL.mdcore3,677 bytesscripts/pedestrian_counting.pyruns10,243 bytes
Read SKILL.md
# Pedestrian VLM Counting
Sends extracted video frames to Vision LLM APIs with carefully engineered prompts for unique pedestrian counting, parses integer results robustly, and writes final counts to a properly formatted Excel file.
## When to Use
- Counting unique pedestrians in surveillance video footage
- Analyzing foot traffic across multiple video files
- Generating Excel reports of pedestrian counts per video
- Using vision AI to perform person re-identification across frames
## Dependencies
This skill depends on `evo-video-frame-extraction` for frame extraction. Import frame extraction functions from that skill.View the complete source on GitHubevo-video-frame-extraction
When your agent uses it
Extract and encode sampled frames from video files for vision AI analysis. Use when you need to process surveillance or other video files by extracting frames at regular intervals, converting them to base64-encoded JPEG images suitable for sending to vision LLM APIs. Handles video file discovery, temporal sampling, MoviePy 2.x resource management, and memory-safe batch processing.
What it loads into context
Frontmatter
81 tokensAlways available to the agent
SKILL.md
637 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- When to Use
- Core Functions
- Usage Example
- Important Notes
Scripts executed separately
scripts/__init__.pyscripts/frame_extraction.py
Files
SKILL.mdcore2,796 bytesSKILL.mdcore2,796 bytesscripts/__init__.pyruns37 bytesscripts/frame_extraction.pyruns6,590 bytes
Read SKILL.md
# Video Frame Extraction
Extracts sampled frames from video files using MoviePy 2.x and encodes them as base64 JPEG strings for downstream vision API consumption.
## When to Use
- Processing surveillance footage for AI analysis
- Extracting representative frames from video files at configurable intervals
- Preparing video frames for vision LLM APIs (OpenAI, Gemini, etc.)
- Batch processing multiple video files in a directory
## Core Functions
The skill provides these functions in `scripts/frame_extraction.py`:View the complete source on GitHubevo-tts-audiobook-synth
When your agent uses it
Converts text chunks into speech audio using cascading fallback (OpenAI TTS -> ElevenLabs -> edge-tts -> gTTS). Handles API auth, rate limiting, MP3 chunk generation, and audio concatenation into a single MP3 file.
What it loads into context
Frontmatter
62 tokensAlways available to the agent
SKILL.md
490 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Key Functions
- Usage
- Technical Notes
Scripts executed separately
scripts/utils.py
Files
SKILL.mdcore1,867 bytesSKILL.mdcore1,867 bytesscripts/utils.pyruns5,364 bytes
Read SKILL.md
# evo-tts-audiobook-synth
Converts text to speech with cascading API fallback and audio concatenation.
## Key Functions
- `synthesize_with_openai(text, output_path)` - Uses OpenAI TTS API (tts-1, 4096 char limit)
- `synthesize_with_elevenlabs(text, output_path)` - Uses ElevenLabs API (client.text_to_speech.convert)
- `synthesize_with_local_tts(text, output_path)` - Uses edge-tts (async) or gTTS as fallback
- `synthesize_text_to_audio(text, output_path)` - Tries OpenAI -> ElevenLabs -> local, returns bytes
- `concatenate_audio_chunks(chunk_files, output_file)` - Concatenates MP3 files using pydub/ffmpeg
## Usage
```pythonView the complete source on GitHubevo-web-essay-scraper
When your agent uses it
Scrapes and extracts clean text from Paul Graham essays on paulgraham.com. Handles legacy table-based HTML, character encoding, and text chunking for TTS APIs.
What it loads into context
Frontmatter
46 tokensAlways available to the agent
SKILL.md
345 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Key Functions
- Essay URLs
- Usage
- Technical Notes
Scripts executed separately
scripts/utils.py
Files
SKILL.mdcore1,326 bytesSKILL.mdcore1,326 bytesscripts/utils.pyruns4,317 bytes
Read SKILL.md
# evo-web-essay-scraper
Scrapes Paul Graham essays and prepares text for TTS consumption.
## Key Functions
- `scrape_pg_essay(url)` - Fetches and extracts clean text from a PG essay URL
- `clean_text(text)` - Cleans text artifacts, encoding issues, nav boilerplate
- `chunk_text(text, max_chars=4000)` - Splits text into API-safe chunks by sentence boundaries
## Essay URLs
- "Do Things that Don't Scale": `http://www.paulgraham.com/ds.html`
- "Founder Mode": `http://www.paulgraham.com/foundermode.html`
View the complete source on GitHubevo-openpyxl-sheet-processor
When your agent uses it
Provides utilities for loading an Excel workbook with openpyxl, copying selected columns from a source sheet to a destination sheet preserving order and headers, appending formula columns, and saving the workbook.
What it loads into context
Frontmatter
50 tokensAlways available to the agent
SKILL.md
584 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Overview
- Key Concepts
- Functions
- Usage
- Depends On
Scripts executed separately
scripts/utils.py
Files
SKILL.mdcore2,470 bytesSKILL.mdcore2,470 bytesSKILL.mdcore2,470 bytesSKILL.mdcore2,470 bytesSKILL.mdcore2,470 bytesscripts/utils.pyruns3,686 bytes
Read SKILL.md
# openpyxl Sheet Processor Skill
## Overview
Utilities for Excel workbook manipulation using openpyxl 3.1.5. Handles loading, column copying, formula insertion, and saving.
## Key Concepts
- openpyxl does NOT evaluate formulas - it stores formula strings
- Do NOT use data_only=True when writing formulas
- Preserve all existing sheets when saving
- Column indices are 1-based in openpyxl
## Functions
### load_workbook_safe(filepath)View the complete source on GitHubevo-powerlifting-dots-formula
When your agent uses it
Provides the exact DOTS scoring formula, sex-specific polynomial coefficients, TotalKg computation rules, edge case handling (negative best lifts, blank values, Mx category), and corresponding Excel formula strings for both TotalKg and DOTS columns.
What it loads into context
Frontmatter
59 tokensAlways available to the agent
SKILL.md
848 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Overview
- Formula
- Required Columns
- Edge Cases
- TotalKg Excel Formula
- DOTS Excel Formula
- Usage
Scripts executed separately
scripts/utils.py
Files
SKILL.mdcore2,700 bytesSKILL.mdcore2,700 bytesscripts/utils.pyruns3,273 bytes
Read SKILL.md
# DOTS Powerlifting Formula Skill
## Overview
The DOTS (Dynamic Objective Team Scoring) formula is a 4th-degree polynomial-based scoring system for normalizing powerlifting performance across body weights.
## Formula
```
DOTS Score = TotalKg × (500 / (A×BW⁴ + B×BW³ + C×BW² + D×BW + E))
```
### Male Coefficients (also used for Mx)
- A = -0.000001093
- B = 0.0007391293
- C = -0.1918759221View the complete source on GitHubevo-pptx-reference-slide
When your agent uses it
Create a reference slide with auto-numbered deduplicated paper titles.
What it loads into context
Frontmatter
25 tokensAlways available to the agent
SKILL.md
84 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Usage
Scripts executed separately
scripts/utils.py
Files
SKILL.mdcore370 bytesSKILL.mdcore370 bytesscripts/utils.pyruns3,406 bytes
Read SKILL.md
# evo-pptx-reference-slide
Create reference slide with numbered bullets.
## Usage
```python
import sys
sys.path.insert(0, '/app/environment/skills/evo-pptx-reference-slide/scripts')
from utils import create_reference_slide, deduplicate_titles
```View the complete source on GitHubevo-pptx-title-detect-format
When your agent uses it
Detect dangling paper titles in PPTX slides and apply font formatting, resizing, and repositioning.
What it loads into context
Frontmatter
32 tokensAlways available to the agent
SKILL.md
115 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Usage
Scripts executed separately
scripts/utils.py
Files
SKILL.mdcore494 bytesSKILL.mdcore494 bytesscripts/utils.pyruns4,326 bytes
Read SKILL.md
# evo-pptx-title-detect-format
Detect and format dangling paper titles.
## Usage
```python
import sys
sys.path.insert(0, '/app/environment/skills/evo-pptx-title-detect-format/scripts')
from utils import detect_dangling_titles, apply_font_formatting_to_shape, resize_textbox_for_single_line, position_bottom_center, extract_title_text
```View the complete source on GitHubevo-pptx-xml-io
When your agent uses it
Low-level PPTX utilities for opening, saving, navigating presentations.
What it loads into context
Frontmatter
26 tokensAlways available to the agent
SKILL.md
98 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Usage
Scripts executed separately
scripts/utils.py
Files
SKILL.mdcore356 bytesSKILL.mdcore356 bytesscripts/utils.pyruns1,030 bytes
Read SKILL.md
# evo-pptx-xml-io
Utilities for PPTX I/O using python-pptx.
## Usage
```python
import sys
sys.path.insert(0, '/app/environment/skills/evo-pptx-xml-io/scripts')
from utils import open_presentation, save_presentation, get_slide_dimensions
```View the complete source on GitHubevo-protein-expression-analysis
When your agent uses it
Use when populating Excel workbooks for quantitative proteomics tasks - computing expression lookups, group statistics, and log2 fold-change values using Python and writing numeric results via openpyxl while preserving cell formatting. Handles two-sheet workbooks (Task + Data) with 2D protein×sample expression matrices.
What it loads into context
Frontmatter
72 tokensAlways available to the agent
SKILL.md
1,121 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- CRITICAL: Write computed numeric values, NOT formulas
- Key facts about the protein_expression.xlsx task
- Critical rules
- Usage
- Alternate usage (step-by-step)
- Output validation
Scripts executed separately
scripts/utils.py
Files
SKILL.mdcore4,491 bytesSKILL.mdcore4,491 bytesSKILL.mdcore4,491 bytesscripts/utils.pyruns13,907 bytes
Read SKILL.md
# evo-protein-expression-analysis
Utilities for populating Excel workbooks with proteomics expression values,
group statistics, and fold-change calculations while preserving all cell formatting.
## CRITICAL: Write computed numeric values, NOT formulas
openpyxl does NOT have a calculation engine. If you write Excel formulas (strings
starting with `=`), they will only be evaluated when the file is opened in Excel.
Tools that read the file with `data_only=True` will see `None` for all formula cells.
**You MUST compute values in Python and write float/int results directly.**
## Key facts about the protein_expression.xlsx taskView the complete source on GitHubevo-proteomics-excel-formulas
When your agent uses it
Use when populating Excel workbooks for quantitative proteomics tasks - writing INDEX/MATCH lookups, AVERAGE/STDEV.S group statistics, and log2 fold-change formulas while preserving cell formatting via openpyxl 3.1.5.
What it loads into context
Frontmatter
63 tokensAlways available to the agent
SKILL.md
998 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Key Principles
- Task Sheet Layout (protein_expression.xlsx)
- Data Sheet Layout
- Usage (one-shot)
- Usage (step-by-step)
- Formula Patterns
Scripts executed separately
scripts/utils.py
Files
SKILL.mdcore3,452 bytesSKILL.mdcore3,452 bytesSKILL.mdcore3,452 bytesscripts/utils.pyruns7,313 bytes
Read SKILL.md
# evo-proteomics-excel-formulas
Utilities for populating Excel workbooks with proteomics Excel formulas
(INDEX-MATCH lookups, AVERAGE, STDEV.S, fold-change) while preserving formatting.
## Key Principles
1. **Write Excel FORMULAS, not computed values** - The task requires formulas.
2. **Load with data_only=False** to preserve existing formulas and formatting.
3. **_xlfn. prefix** for STDEV.S: openpyxl requires `_xlfn.STDEV.S(...)` to avoid #NAME? errors.
4. **AVERAGE** is a core OOXML function - no prefix needed.
5. **Data is log2-transformed**: Log2FC = Treated_Mean - Control_Mean; FC = 2^Log2FC.
6. **Preserve formatting**: Setting cell.value preserves existing fill, font, border.
7. **Use wb["SheetName"]** not deprecated get_sheet_by_name().View the complete source on GitHubevo-scala-idiom-mapping
When your agent uses it
Maps Python constructs to idiomatic Scala 2.13 equivalents.
What it loads into context
Frontmatter
26 tokensAlways available to the agent
SKILL.md
135 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Usage
Scripts executed separately
scripts/idiom_mapper.py
Files
SKILL.mdcore519 bytesSKILL.mdcore519 bytesscripts/idiom_mapper.pyruns397 bytes
Read SKILL.md
# evo-scala-idiom-mapping
Maps Python→Scala: enum→sealed trait, dataclass→case class, ABC→trait, snake_case→camelCase, Optional→Option, datetime→java.time, Decimal→BigDecimal, Generic variance (+/-), collections.
## Usage
```python
import sys
sys.path.insert(0, '/app/environment/skills/evo-scala-idiom-mapping/scripts')
from idiom_mapper import snake_to_camel, map_python_type_to_scala
```View the complete source on GitHubevo-scala-tokenizer-generator
When your agent uses it
Generates complete Scala 2.13 Tokenizer.scala from Python Tokenizer.py translation.
What it loads into context
Frontmatter
28 tokensAlways available to the agent
SKILL.md
102 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Usage
Scripts executed separately
scripts/generate.py
Files
SKILL.mdcore457 bytesSKILL.mdcore457 bytesscripts/generate.pyruns12,738 bytes
Read SKILL.md
# evo-scala-tokenizer-generator
Produces /root/Tokenizer.scala with all classes/traits translated from Python.
## Usage
```python
import sys
sys.path.insert(0, '/app/environment/skills/evo-scala-tokenizer-generator/scripts')
from generate import generate_scala_file
generate_scala_file('/root/Tokenizer.scala')
```View the complete source on GitHubevo-dicke-model-simulation
When your agent uses it
Builds the open Dicke model Hamiltonian and Lindblad collapse operators in the full 2^N tensor product Hilbert space, solves for the steady-state density matrix, and extracts the reduced cavity state via partial trace.
What it loads into context
Frontmatter
55 tokensAlways available to the agent
SKILL.md
478 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Usage
- Key Functions
Scripts executed separately
scripts/utils.py
Files
SKILL.mdcore1,700 bytesSKILL.mdcore1,700 bytesscripts/utils.pyruns4,313 bytes
Read SKILL.md
# evo-dicke-model-simulation
Simulates the open Dicke model with N two-level systems coupled to a cavity mode.
Supports local dephasing, local emission, local pumping, collective emission, and collective pumping.
## Usage
```python
import sys
sys.path.insert(0, '/app/environment/skills/evo-dicke-model-simulation/scripts')
from utils import (
build_local_spin_op, build_collective_spin_ops,
build_dicke_hamiltonian, build_collapse_operators,
solve_steady_state, get_cavity_stateView the complete source on GitHubevo-wigner-csv-export
When your agent uses it
Computes the Wigner function of a bosonic density matrix on a specified phase-space grid using QuTiP and exports the result as a CSV file.
What it loads into context
Frontmatter
41 tokensAlways available to the agent
SKILL.md
266 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Usage
- Key Functions
Scripts executed separately
scripts/utils.py
Files
SKILL.mdcore937 bytesSKILL.mdcore937 bytesscripts/utils.pyruns1,959 bytes
Read SKILL.md
# evo-wigner-csv-export
Computes Wigner functions on phase-space grids and exports to CSV.
## Usage
```python
import sys
sys.path.insert(0, '/app/environment/skills/evo-wigner-csv-export/scripts')
from utils import compute_wigner_function, save_wigner_to_csv
# Compute Wigner function on 1000x1000 grid over [-6,6]
W, xvec, yvec = compute_wigner_function(rho_cavity, n_points=1000)
View the complete source on GitHubevo-r2r-linearization
When your agent uses it
Derives linearized state-space model (A, B matrices) for 6-section R2R system, computes steady-state operating points, discretizes, and computes LQR gain.
What it loads into context
Frontmatter
48 tokensAlways available to the agent
SKILL.md
324 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Usage
- Key Functions
Scripts executed separately
scripts/utils.py
Files
SKILL.mdcore1,113 bytesSKILL.mdcore1,113 bytesscripts/utils.pyruns6,408 bytes
Read SKILL.md
# evo-r2r-linearization
Computes linearized state-space model for R2R web handling systems.
## Usage
```python
import sys
sys.path.insert(0, '/app/environment/skills/evo-r2r-linearization/scripts')
from utils import (
compute_steady_state_velocities,
compute_steady_state_torques,
build_continuous_AB,
discretize_system,
compute_lqr_gain,View the complete source on GitHubevo-r2r-mpc-controller
When your agent uses it
Implements MPC controller with prediction matrices, QP formulation, simulation loop for R2R web handling. Generates controller_params.json, control_log.json, and metrics.json.
What it loads into context
Frontmatter
45 tokensAlways available to the agent
SKILL.md
373 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Usage
- Key Functions
- Output Files
Scripts executed separately
scripts/utils.py
Files
SKILL.mdcore1,427 bytesSKILL.mdcore1,427 bytesscripts/utils.pyruns3,467 bytes
Read SKILL.md
# evo-r2r-mpc-controller
MPC controller for 6-section R2R system with reference step tracking.
## Usage
```python
import sys
sys.path.insert(0, '/app/environment/skills/evo-r2r-mpc-controller/scripts')
from utils import (
build_prediction_matrices,
build_qp_matrices,
solve_mpc_step,
run_simulation_loop,
compute_performance_metrics,View the complete source on GitHubevo-nextjs-api-optimization
When your agent uses it
Identifies and fixes performance anti-patterns in Next.js API routes including artificial delays, N+1 sequential fetch patterns, missing caching headers, and unnecessary data processing.
What it loads into context
Frontmatter
44 tokensAlways available to the agent
SKILL.md
305 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Key Patterns
- Usage
Scripts executed separately
scripts/utils.py
Files
SKILL.mdcore1,365 bytesSKILL.mdcore1,365 bytesscripts/utils.pyruns3,704 bytes
Read SKILL.md
# evo-nextjs-api-optimization
Optimizes Next.js API routes by:
1. Removing artificial delays (setTimeout in production)
2. Parallelizing sequential awaits with Promise.all
3. Adding caching headers (Cache-Control)
4. Optimizing data fetching patterns
## Key Patterns
### Sequential Awaits → Promise.all
Anti-pattern:
```typescript
const user = await fetchUser();View the complete source on GitHubevo-nextjs-bundle-reduction
When your agent uses it
Identifies and fixes bundle size issues including wildcard/barrel imports, missing dynamic imports for heavy components, unnecessary use client directives, and useEffect-based data fetching.
What it loads into context
Frontmatter
44 tokensAlways available to the agent
SKILL.md
362 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Key Patterns
- Usage
Scripts executed separately
scripts/utils.py
Files
SKILL.mdcore1,571 bytesSKILL.mdcore1,571 bytesscripts/utils.pyruns4,650 bytes
Read SKILL.md
# evo-nextjs-bundle-reduction
Reduces client bundle size by:
1. Converting barrel lodash imports to individual module imports
2. Applying next/dynamic for code splitting heavy components
3. Minimizing 'use client' boundary scope
4. Converting client-side useEffect fetches to server-side patterns
## Key Patterns
### Barrel Lodash Imports → Individual Imports
Anti-pattern:
```typescript
import { groupBy, sortBy, meanBy } from 'lodash';View the complete source on GitHubevo-nextjs-render-optimization
When your agent uses it
Identifies and fixes excessive React re-rendering issues including missing React.memo, unmemoized callbacks/computations, and context overloading.
What it loads into context
Frontmatter
39 tokensAlways available to the agent
SKILL.md
336 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Key Patterns
- Usage
Scripts executed separately
scripts/utils.py
Files
SKILL.mdcore1,430 bytesSKILL.mdcore1,430 bytesscripts/utils.pyruns4,756 bytes
Read SKILL.md
# evo-nextjs-render-optimization
Optimizes React rendering by:
1. Wrapping frequently re-rendered components in React.memo
2. Adding useMemo for expensive computations
3. Adding useCallback for callback stability
4. Splitting overloaded contexts
## Key Patterns
### React.memo for ProductCard
Anti-pattern:
```typescript
export function ProductCard({ product, onAddToCart, isInCart }: Props) { ... }View the complete source on GitHubevo-excel-data-extraction
When your agent uses it
Utilities for exploring and extracting data from complex, multi-sheet Excel workbooks with irregular formatting. Provides functions to discover sheet structure, locate gold prices in IMF data, and extract country reserve data.
What it loads into context
Frontmatter
49 tokensAlways available to the agent
SKILL.md
494 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Key Functions
- Usage
- Data Layout Notes
Scripts executed separately
scripts/utils.py
Files
SKILL.mdcore1,995 bytesSKILL.mdcore1,995 bytesscripts/utils.pyruns4,370 bytes
Read SKILL.md
# evo-excel-data-extraction
Utilities for reading IMF commodity price data and template workbook structures.
## Key Functions
- `extract_gold_price_series(filepath)` - Extract gold price (US$/troy oz) time series from IMF file. Returns list of (date_str, price) tuples.
- `extract_country_reserve_data(filepath, sheet_name, year_row=18)` - Extract country gold reserves from Value/Volume sheets. Returns dict with country data.
- `extract_total_reserves_data(filepath, year_row=18)` - Extract total reserves for 2025.
- `explore_sheet_structure(filepath)` - Get sheet dimensions and info.
- `extract_country_names_from_desc(desc_str)` - Parse country name from column description.
## Usage
View the complete source on GitHubevo-excel-financial-formulas
When your agent uses it
Utilities for writing financial Excel formulas (log returns, rolling volatility, annualized volatility, XLOOKUP/INDEX+MATCH, RaR calculations) into openpyxl workbooks and triggering LibreOffice headless recalculation.
What it loads into context
Frontmatter
56 tokensAlways available to the agent
SKILL.md
549 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Key Functions
- Usage
- Formula Details
Scripts executed separately
scripts/utils.py
Files
SKILL.mdcore2,004 bytesSKILL.mdcore2,004 bytesscripts/utils.pyruns2,432 bytes
Read SKILL.md
# evo-excel-financial-formulas
Write financial formulas into Excel workbooks and recalculate with LibreOffice.
## Key Functions
- `write_gold_price_sheet(wb, gold_series)` - Populate gold prices into Gold price sheet col B
- `write_log_return_formulas(wb, start_row, end_row)` - Write =LN(Bn/Bn-1)*100 in col C
- `write_volatility_formulas(wb, start_row, end_row)` - Write STDEV.S formulas in cols D (3-month) and E (12-month)
- `write_answer_sheet_step1(wb)` - Fill z-score, volatilities in Answer sheet
- `write_answer_sheet_step2(wb, value_countries, volume_countries, gold_avg_price)` - Fill country reserves and exposure
- `write_answer_sheet_step3(wb, step2_countries, total_reserves_data)` - Fill RaR calculations
- `recalculate_with_libreoffice(filepath)` - Force formula recalculation
- `create_output_workbook(template_path, output_path, ...)` - Main orchestrator functionView the complete source on GitHubevo-sales-pivot-analysis
When your agent uses it
End-to-end demographic analysis pipeline that extracts population data from PDF, reads income data from Excel, merges datasets, computes range-based income quartiles, generates four openpyxl pivot table objects, and exports a five-sheet Excel workbook.
What it loads into context
Frontmatter
56 tokensAlways available to the agent
SKILL.md
739 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- CRITICAL: Native Pivot Tables Required
- Pipeline Steps
- Usage
- Sheet Structure
- Quartile Logic
- Data Notes
Scripts executed separately
scripts/run_pipeline.py
Files
SKILL.mdcore2,820 bytesSKILL.mdcore2,820 bytesSKILL.mdcore2,820 bytesscripts/run_pipeline.pyruns21,806 bytes
Read SKILL.md
# evo-sales-pivot-analysis
Complete pipeline for demographic data analysis: extracts population data from multi-page PDF tables,
ingests income data from Excel, merges on SA2_CODE, computes range-based quartile classifications and
derived columns, builds **native openpyxl pivot table objects**, and exports a multi-sheet Excel report.
## CRITICAL: Native Pivot Tables Required
The output Excel file MUST contain **actual Excel pivot table objects** (not flat summary tables).
The verifier checks `worksheet._pivots[0]` — pandas `.to_excel()` does NOT create these.
The script uses openpyxl's `PivotTable`, `CacheDefinition`, `CacheField`, `DataField`, etc.
## Pipeline Steps
View the complete source on GitHubevo-sec13f-analyzer
When your agent uses it
Toolkit for parsing SEC Form 13F-HR quarterly TSV datasets. Loads COVERPAGE/INFOTABLE/SUMMARYPAGE with safe dtypes (CUSIPs as zero-padded strings, VALUE as numeric dollars), fuzzy-matches fund manager names with RapidFuzz, retrieves fund AUM, deduplicates equity holdings (filtering options), compares holdings across quarters, and ranks top holders of a given CUSIP. Use whenever working with /root/2025-qN 13F TSV files.
What it loads into context
Frontmatter
113 tokensAlways available to the agent
SKILL.md
1,013 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Key facts
- Importing
- Typical workflow
- Functions (scripts/utils.py)
Scripts executed separately
scripts/utils.py
Files
SKILL.mdcore3,444 bytesSKILL.mdcore3,444 bytesSKILL.mdcore3,444 bytesscripts/utils.pyruns5,522 bytes
Read SKILL.md
# evo-sec13f-analyzer
Utilities for SEC Form 13F-HR quarterly TSV analytics.
## Key facts
- SEC EDGAR Release 22.4.1 (Jan 3, 2023): VALUE column is in **exact dollars** (multiplier = 1) for all filings from 2023 onward. Use `value_multiplier=1` for the 2025-q2 / 2025-q3 data in this task.
- CUSIP is a 9-char alphanumeric. Always load as string and zero-pad to length 9 to preserve leading zeros (Apple = `037833100`).
- TSV columns: tab-delimited, UTF-8.
- `PUTCALL` blank = equity; `PUT` / `CALL` = options. Exclude options when counting equity positions.
- AUM (gross portfolio value) lives in `SUMMARYPAGE.TABLEVALUETOTAL`. Number of equity positions (unique CUSIPs) is computed from INFOTABLE.
- Fund manager names vary in casing/punctuation. Use RapidFuzz `process.extract` with `fuzz.WRatio` and `utils.default_process` for entity resolution against `COVERPAGE.FILINGMANAGER_NAME`.
## Importing
View the complete source on GitHubevo-seismic-data-preprocessing
When your agent uses it
Loads seismic waveform data from .npz files and converts them into ObsPy Stream objects ready for SeisBench model inference. Handles channel identification, reordering to Z/N/E convention, float32 conversion, detrending, and resampling to 100 Hz.
What it loads into context
Frontmatter
63 tokensAlways available to the agent
SKILL.md
495 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Overview
- Key Knowledge
- Usage
- Functions
Scripts executed separately
scripts/utils.py
Files
SKILL.mdcore1,991 bytesSKILL.mdcore1,991 bytesscripts/utils.pyruns4,964 bytes
Read SKILL.md
# evo-seismic-data-preprocessing
## Overview
This skill handles all data I/O from .npz seismic trace files and transforms them into properly formatted ObsPy Stream objects with correct channel ordering (Z, N, E), sampling rate (100 Hz), and data types (float32).
## Key Knowledge
- NPZ files contain: data (12000x3), dt (sampling interval), channels (comma-separated like "DPE,DPN,DPZ")
- SeisBench models expect Z, N, E channel order - must reorder from whatever order is in the file
- Channel codes ending in Z=Vertical, N=North, E=East
- Data must be float32 for PyTorch models
- Detrend (demean) before inference
- Resample to 100 Hz if not already at that rate
## UsageView the complete source on GitHubevo-seismic-phase-picking
When your agent uses it
Runs SeisBench pretrained PhaseNet model on ObsPy Streams to detect P and S wave arrivals, extracts pick indices, and writes results to CSV.
What it loads into context
Frontmatter
41 tokensAlways available to the agent
SKILL.md
375 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Overview
- Key Knowledge
- Usage
- Functions
Scripts executed separately
scripts/utils.py
Files
SKILL.mdcore1,532 bytesSKILL.mdcore1,532 bytesscripts/utils.pyruns4,590 bytes
Read SKILL.md
# evo-seismic-phase-picking
## Overview
Runs SeisBench PhaseNet model inference on preprocessed ObsPy Streams to detect P and S wave arrivals. Extracts pick indices mapped to original sample coordinates and writes CSV output.
## Key Knowledge
- Use PhaseNet with "stead" weights for best generalization
- P_threshold=0.3, S_threshold=0.3 for good recall
- model.classify() handles sliding windows automatically
- Convert pick times back to original array indices using UTCDateTime math
- Output CSV: file_name, phase, pick_idx
## Usage
```pythonView the complete source on GitHubevo-atheris-fuzz-driver
When your agent uses it
Creates Atheris-based coverage-guided fuzz drivers for Python libraries using FuzzedDataProvider for structured input generation. Includes templates and patterns for different library types (parsers, formatters, serializers, ML frameworks).
What it loads into context
Frontmatter
56 tokensAlways available to the agent
SKILL.md
396 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Driver Design Principles
- Supported Libraries
- Key Functions
- Usage
Scripts executed separately
scripts/fuzz_driver.py
Files
SKILL.mdcore1,706 bytesSKILL.mdcore1,706 bytesSKILL.mdcore1,706 bytesscripts/fuzz_driver.pyruns6,305 bytes
Read SKILL.md
# Atheris Fuzz Driver Generator
Generates fuzz.py harness files for Python libraries with proper Atheris instrumentation, FuzzedDataProvider usage, and exception handling.
## Driver Design Principles
1. Import target library inside `atheris.instrument_imports()` context manager
2. Use `FuzzedDataProvider` to generate structured typed inputs
3. Catch only expected exceptions (ValueError, TypeError, domain-specific errors)
4. Guard with `if __name__ == "__main__":` block
5. Use `atheris.Setup(sys.argv, TestOneInput)` then `atheris.Fuzz()`
## Supported Libraries
View the complete source on GitHubevo-fuzz-env-runner
When your agent uses it
Sets up Python virtual environments using uv for each library, installs dependencies from project configuration files, and executes the fuzzer for a specified duration with proper log redirection.
What it loads into context
Frontmatter
44 tokensAlways available to the agent
SKILL.md
316 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Workflow
- Key Functions
- Usage
Scripts executed separately
scripts/runner.py
Files
SKILL.mdcore1,296 bytesSKILL.mdcore1,296 bytesscripts/runner.pyruns4,124 bytes
Read SKILL.md
# Fuzz Environment Runner
Sets up isolated Python virtual environments using `uv`, installs library dependencies and atheris, runs fuzz.py with LibFuzzer flags, and captures output to fuzz.log.
## Workflow
1. Create .venv using `uv venv .venv` in each library directory
2. Install atheris and library dependencies via `uv pip install`
3. Run fuzzer with `-max_total_time=10` flag
4. Capture stdout+stderr to fuzz.log
## Key Functions
- `setup_venv_with_uv(lib_path)` - Create virtual environmentView the complete source on GitHubevo-python-library-discovery
When your agent uses it
Detects Python libraries/packages in a directory by checking for pyproject.toml, setup.py, setup.cfg, or other standard Python project markers. Provides utilities to list library paths and analyze their structure, entry points, and key functions for testing.
What it loads into context
Frontmatter
59 tokensAlways available to the agent
SKILL.md
331 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Detection Heuristics
- Key Functions
- Usage
Scripts executed separately
scripts/discover.py
Files
SKILL.mdcore1,507 bytesSKILL.mdcore1,507 bytesscripts/discover.pyruns6,614 bytes
Read SKILL.md
# Python Library Discovery
This skill identifies Python library directories within a given base path and analyzes their public APIs to produce testing notes.
## Detection Heuristics
A subdirectory is considered a Python library if it contains any of:
- `pyproject.toml` (modern PEP 517/621 standard)
- `setup.py` (legacy setuptools)
- `setup.cfg` (legacy setuptools config)
## Key Functions
- `find_python_libraries(base_dir)` - Scan directory for Python libraries, returns list of absolute pathsView the complete source on GitHubevo-macro-demand-shock-scenarios
When your agent uses it
Builds demand-side investment shock model on NA sheet with bell-shaped spending, currency conversion, deflation, import adjustment, multiplier. Creates 3 scenarios.
What it loads into context
Frontmatter
44 tokensAlways available to the agent
SKILL.md
204 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Usage
- Bell Shape: [2%,7%,15%,22%,24%,18%,9%,3%]
- Exchange Rate: 2.746 GEL/USD
- Scenarios: 1(mult=0.8,theta=SUT), 2(mult=1.0,theta=SUT), 3(mult=0.8,theta=0.5)
Scripts executed separately
scripts/utils.py
Files
SKILL.mdcore707 bytesSKILL.mdcore707 bytesscripts/utils.pyruns4,670 bytes
Read SKILL.md
# evo-macro-demand-shock-scenarios
## Usage
```python
import sys
sys.path.insert(0, '/app/environment/skills/evo-macro-demand-shock-scenarios/scripts')
from utils import create_scenario_tables, recalculate_workbook
create_scenario_tables(wb)
wb.save('test - demand.xlsx')
recalculate_workbook('test - demand.xlsx')
```
## Bell Shape: [2%,7%,15%,22%,24%,18%,9%,3%]View the complete source on GitHubevo-macro-sut-import-share
When your agent uses it
Computes the import content share of investment (theta) from GeoStat Supply and Use Tables using the proportionality assumption. Links SUT data to a SUT Calc sheet, calculates product-level import-to-supply ratios, and derives the aggregate import content share for GFCF. Use when estimating import leakage for demand-side investment shock analysis.
What it loads into context
Frontmatter
79 tokensAlways available to the agent
SKILL.md
464 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- What it does
- Methodology: Proportionality Assumption
- Data Sources
- Dependencies
Scripts executed separately
scripts/utils.py
Files
SKILL.mdcore1,790 bytesscripts/utils.pyruns1,896 bytes
Read SKILL.md
# evo-macro-sut-import-share
This skill handles the second stage of the macro demand-side accounting pipeline: computing the import content share of investment from Supply and Use Tables.
## What it does
1. **Creates SUT Calc sheet** with columns linking to SUPPLY and USE data:
- Col A: Product code (rows 4-41 from SUT, 38 products)
- Col B: Product name
- Col C: Total Supply at purchasers prices (from SUPPLY sheet col AS)
- Col D: Imports total (from SUPPLY sheet col AR)
- Col E: Import share per product = D/C (mu_i)
- Col F: GFCF by product (from USE sheet col AT)
- Col G: Imported GFCF = E*F (mu_i * I_i)View the complete source on GitHubevo-macro-weo-data
When your agent uses it
Populates WEO_Data sheet with IMF WEO data for Georgia, extends GDP deflator and real GDP projections to 2043, and copies GeoStat SUT sheets into the workbook.
What it loads into context
Frontmatter
49 tokensAlways available to the agent
SKILL.md
384 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Purpose
- Key Knowledge
- Usage
- Functions
Scripts executed separately
scripts/utils.py
Files
SKILL.mdcore1,419 bytesSKILL.mdcore1,419 bytesscripts/utils.pyruns5,293 bytes
Read SKILL.md
# evo-macro-weo-data
## Purpose
Handles IMF WEO data ingestion and projection extension for Georgia macro model.
## Key Knowledge
- WEO CSV has: Year, Real GDP (bn Lari), Real GDP Growth (%), GDP Deflator for 2020-2027
- Real GDP growth rate from 2027 is held constant through 2043
- GDP Deflator extended using average of last 4 years growth rates as fixed anchor
- GeoStat SUT 38x38 sheets copied with original names preserved
## Usage
```python
import sysView the complete source on GitHubevo-simpo-code-reproduction
When your agent uses it
Implements the SimPO (Simple Preference Optimization) loss function and handles environment setup, execution, and result saving for code reproduction tasks.
What it loads into context
Frontmatter
38 tokensAlways available to the agent
SKILL.md
915 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Overview
- Key Concepts (from the paper)
- Environment Setup
- Usage
- Common Pitfalls
Scripts executed separately
scripts/run_and_save.pyscripts/simpo_loss_impl.py
Files
SKILL.mdcore3,475 bytesSKILL.mdcore3,475 bytesSKILL.mdcore3,475 bytesSKILL.mdcore3,475 bytesSKILL.mdcore3,475 bytesscripts/run_and_save.pyruns6,395 bytesscripts/simpo_loss_impl.pyruns9,981 bytes
Read SKILL.md
# evo-simpo-code-reproduction
## Overview
Complete skill for reproducing the SimPO (Simple Preference Optimization) loss function from the paper by Meng et al. (2024). Handles implementation of the `simpo_loss` method, environment setup, unit test execution, and saving results.
## Key Concepts (from the paper)
### SimPO Loss Formula
```
L_SimPO = -log(sigmoid(beta/|y_w| * sum(log π(y_w|x)) - beta/|y_l| * sum(log π(y_l|x)) - gamma))
```
### Critical Implementation Details
1. **Inputs are pre-normalized**: `policy_chosen_logps` and `policy_rejected_logps` are already length-averaged (mean log probs per token) before entering `simpo_loss`. The averaging happens in `get_batch_logps` with `average_log_prob=True`.View the complete source on GitHubevo-software-dependency-audit
When your agent uses it
Security audit skill for scanning dependency files (e.g., package-lock.json) using Trivy offline scanner to identify HIGH/CRITICAL vulnerabilities and produce CSV reports.
What it loads into context
Frontmatter
44 tokensAlways available to the agent
SKILL.md
996 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- CRITICAL: You MUST Use Trivy (Not npm audit)
- Quickest Path to Solution
- Alternative: Use as a Python Library
- Why Trivy and Not npm audit
- Technical Details
- Functions in scripts/utils.py
Scripts executed separately
scripts/run_audit.pyscripts/utils.py
Files
SKILL.mdcore4,028 bytesSKILL.mdcore4,028 bytesSKILL.mdcore4,028 bytesSKILL.mdcore4,028 bytesscripts/run_audit.pyruns1,149 bytesscripts/utils.pyruns17,269 bytes
Read SKILL.md
# evo-software-dependency-audit
## CRITICAL: You MUST Use Trivy (Not npm audit)
**DO NOT use `npm audit`, `yarn audit`, `snyk`, or any other tool.** The ONLY correct tool for this task is **Trivy** with its pre-built offline vulnerability database. Using any other tool will produce incorrect results because different tools use different vulnerability databases with different CVE mappings, CVSS scores, and fixed version information.
Trivy is already installed and its offline database is pre-loaded. You do not need internet access.
## Quickest Path to Solution
A complete, ready-to-run Python script is provided. Simply execute it:
```bash
python3 /root/.claude/skills/evo-software-dependency-audit/scripts/run_audit.pyView the complete source on GitHubevo-speaker-diarization-subtitles
When your agent uses it
End-to-end speaker diarization and subtitle generation pipeline for video/audio files. Extracts audio via ffmpeg, performs VAD (silero-vad), extracts ECAPA-TDNN speaker embeddings (speechbrain), clusters speakers (agglomerative clustering with cosine distance), transcribes with OpenAI Whisper, aligns transcripts to speakers via IoU overlap, and outputs RTTM, ASS subtitles, and a JSON report.
What it loads into context
Frontmatter
96 tokensAlways available to the agent
SKILL.md
635 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Pipeline
- Usage
- Dependencies
- Key Domain Notes
Files
SKILL.mdcore2,526 bytesSKILL.mdcore2,526 bytes
Read SKILL.md
# evo-speaker-diarization-subtitles
End-to-end speaker diarization and subtitle generation pipeline for video/audio files.
## Pipeline
1. **Audio extraction**: ffmpeg → 16kHz mono 16-bit PCM WAV
2. **Voice Activity Detection**: silero-vad (with fallback to torch.hub if direct import unavailable)
3. **Speaker embedding extraction**: SpeechBrain ECAPA-TDNN (`spkrec-ecapa-voxceleb`)
4. **Speaker clustering**: Agglomerative clustering with cosine distance + silhouette-based speaker count selection
5. **Transcription**: OpenAI Whisper with word-level timestamps
6. **Alignment**: Word-level IoU overlap mapping from Whisper words to diarized speaker segments
7. **Output generation**: RTTM (pyannote.core or manual), ASS subtitles, JSON report
## UsageView the complete source on GitHubevo-spring-boot-jakarta-migration
When your agent uses it
Migrate a Java 8/Spring Boot 2.7 project to Java 21/Spring Boot 3.2 with comprehensive handling of namespace changes, security config, Hibernate 6, JJWT 0.12.x, and RestClient migration.
What it loads into context
Frontmatter
66 tokensAlways available to the agent
SKILL.md
757 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Purpose
- Key Migration Areas
- Usage
- Scripts
- Domain Knowledge References
Scripts executed separately
scripts/file_utils.pyscripts/namespace_migrator.pyscripts/pom_migrator.py
Files
SKILL.mdcore3,011 bytesSKILL.mdcore3,011 bytesscripts/file_utils.pyruns1,841 bytesscripts/namespace_migrator.pyruns4,436 bytesscripts/pom_migrator.pyruns9,174 bytes
Read SKILL.md
# Spring Boot 2.7 → 3.2 Jakarta Migration Skill
## Purpose
Migrate a Java 8/Spring Boot 2.7 user management microservice to Java 21/Spring Boot 3.2, covering all layers of the application stack.
## Key Migration Areas
1. **pom.xml**: Update parent to 3.2.x, java.version to 21, maven-compiler-plugin with `-parameters`, replace jjwt 0.9.x with modular 0.12.x, remove jaxb-api
2. **Jakarta namespace**: Replace javax.persistence → jakarta.persistence, javax.validation → jakarta.validation, javax.servlet → jakarta.servlet. **Preserve** javax.crypto, javax.sql, javax.net (Java SE packages)
3. **Spring Security 6**: Remove WebSecurityConfigurerAdapter, use SecurityFilterChain bean, Lambda DSL, authorizeHttpRequests + requestMatchers, @EnableMethodSecurity
4. **JJWT 0.12.x API**: Migrate from `Jwts.parser().setSigningKey()` to `Jwts.parser().verifyWith().build().parseSignedClaims()`, from `Jwts.builder().signWith(SignatureAlgorithm.HS512, key)` to `Jwts.builder().signWith(key)`
5. **Hibernate 6**: Remove versioned dialect references, use GenerationType.IDENTITY explicitly, update H2Dialect to unversioned form
6. **RestTemplate → RestClient**: Migrate to fluent RestClient API
7. **Application properties**: Update hibernate dialect class names, remove deprecated properties
View the complete source on GitHubevo-suricata-custom-exfil
When your agent uses it
Generates and validates Suricata 7.0 rules for detecting data exfiltration hidden in HTTP telemetry traffic, using sticky buffers, exact URI matching, header inspection, and PCRE body pattern matching.
What it loads into context
Frontmatter
53 tokensAlways available to the agent
SKILL.md
1,272 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Description
- Domain Knowledge
- Usage
- Files
Scripts executed separately
scripts/generate_rule.py
Files
SKILL.mdcore4,945 bytesSKILL.mdcore4,945 bytesSKILL.mdcore4,945 bytesscripts/generate_rule.pyruns17,877 bytes
Read SKILL.md
# evo-suricata-custom-exfil
## Description
Generates Suricata 7.0 rules for detecting data exfiltration hidden in HTTP telemetry traffic.
Handles all five detection conditions with proper sticky buffer syntax, URL-decode transforms,
parameter boundary awareness, and PCRE anchoring to minimize false positives and false negatives.
## Domain Knowledge
### Suricata 7.0 Rule Structure
- Header: `alert http any any -> any any` — use `alert http` to leverage Application Layer
Protocol Identification (ALPI); avoids port-dependent matching.
- Use `any any -> any any` when both source and destination may be internal (e.g., 10.x to 10.x).
- Options in parentheses, semicolon-delimited.View the complete source on GitHubevo-syzkaller-ppdev-syzlang
When your agent uses it
Generates syzkaller syzlang descriptions for the Linux ppdev (parallel port) driver, covering all 28 ioctls (including 5 obsolete ones), structs, IEEE 1284 mode flags, and PP flags with architecture-specific constants for amd64 and 386.
What it loads into context
Frontmatter
72 tokensAlways available to the agent
SKILL.md
818 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Overview
- Key Domain Knowledge
- Usage
- Verification
Scripts executed separately
scripts/generate.py
Files
SKILL.mdcore2,711 bytesSKILL.mdcore2,711 bytesSKILL.mdcore2,711 bytesscripts/generate.pyruns16,570 bytes
Read SKILL.md
# evo-syzkaller-ppdev-syzlang
Generates complete syzkaller syzlang device driver descriptions for the Linux ppdev (parallel port) subsystem.
## Overview
Produces two files:
- `dev_ppdev.txt` — syzlang descriptions with includes, resource, opener, all 28 ioctl variants, struct, and flag groups
- `dev_ppdev.txt.const` — architecture-specific constant values for amd64 and 386
## Key Domain Knowledge
### IOCTL Encoding (x86)
- ppdev uses magic type char `'p'` (0x70) for all ioctls
- `_IO`: dir=0, size=0View the complete source on GitHubevo-cluster-naming
When your agent uses it
Assign human-readable, non-overlapping representative names to clusters using TF-IDF and centroid proximity.
What it loads into context
Frontmatter
29 tokensAlways available to the agent
SKILL.md
102 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Usage
Scripts executed separately
scripts/name_utils.py
Files
SKILL.mdcore447 bytesSKILL.mdcore447 bytesscripts/name_utils.pyruns7,431 bytes
Read SKILL.md
# Cluster Naming
## Usage
```python
import sys; sys.path.insert(0, '/app/environment/skills/evo-cluster-naming/scripts')
from name_utils import name_all_levels
level_names = name_all_levels(label_matrix, texts, embeddings)
# returns dict: (level_idx, cluster_path_tuple) -> name string
```View the complete source on GitHubevo-semantic-hierarchical-clustering
When your agent uses it
Generate sentence embeddings and build a balanced 5-level hierarchy via recursive top-down clustering.
What it loads into context
Frontmatter
30 tokensAlways available to the agent
SKILL.md
126 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Usage
Scripts executed separately
scripts/cluster_utils.py
Files
SKILL.mdcore552 bytesSKILL.mdcore552 bytesscripts/cluster_utils.pyruns4,017 bytes
Read SKILL.md
# Semantic Hierarchical Clustering
## Usage
```python
import sys; sys.path.insert(0, '/app/environment/skills/evo-semantic-hierarchical-clustering/scripts')
from cluster_utils import generate_normalized_embeddings, recursive_top_down_cluster
embeds = generate_normalized_embeddings(list_of_strings)
label_matrix = recursive_top_down_cluster(embeds, k_per_level=[14, 8, 6, 5, 4])
```View the complete source on GitHubevo-taxonomy-data-pipeline
When your agent uses it
Load, normalize, and output e-commerce category taxonomy data using Pandas 2.2.0-safe patterns.
What it loads into context
Frontmatter
34 tokensAlways available to the agent
SKILL.md
193 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Usage
Scripts executed separately
scripts/utils.py
Files
SKILL.mdcore853 bytesSKILL.mdcore853 bytesscripts/utils.pyruns3,216 bytes
Read SKILL.md
# Taxonomy Data Pipeline
Loads Amazon/Facebook/Google CSVs, normalizes category_path text, splits hierarchical levels, writes outputs.
## Usage
```python
import sys; sys.path.insert(0, '/app/environment/skills/evo-taxonomy-data-pipeline/scripts')
from utils import load_source_csvs, normalize_category_paths, split_hierarchy_columns, write_unified_outputs
df = load_source_csvs('/root/data/amazon_product_categories.csv','/root/data/fb_product_categories.csv','/root/data/google_shopping_product_categories.csv')
df = normalize_category_paths(df)
df = split_hierarchy_columns(df)
write_unified_outputs(df, '/root/output/unified_taxonomy_full.csv', '/root/output/unified_taxonomy_hierarchy.csv')
```View the complete source on GitHubevo-threejs-scene-parser
When your agent uses it
Parse a Three.js createScene() file in headless Node.js, identify part-level structure (Groups and standalone Meshes), and export OBJ files for both individual sub-meshes per part and merged part assemblies (links). Use when extracting decomposed 3D object structure from Three.js scene definitions.
What it loads into context
Frontmatter
72 tokensAlways available to the agent
SKILL.md
699 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Output Layout
- Part Identification Rules
- Usage (Python)
- Usage (CLI)
- Key Implementation Notes
Scripts executed separately
scripts/package.jsonscripts/parser.mjsscripts/run.py
Files
SKILL.mdcore2,793 bytesSKILL.mdcore2,793 bytesSKILL.mdcore2,793 bytesSKILL.mdcore2,793 bytesscripts/package.jsonruns267 bytesscripts/parser.mjsruns5,857 bytesscripts/run.pyruns1,051 bytes
Read SKILL.md
# evo-threejs-scene-parser
Parses a Three.js scene file (one that exports a `createScene()` function) using a headless Node.js runtime, then exports each part as Wavefront OBJ files in two views:
- `part_meshes/<part_name>/<mesh_name>.obj` — one OBJ per direct child Mesh of each Group
- `links/<part_name>.obj` — merged OBJ of all direct child meshes of the Group (NOT nested sub-group descendants)
## Output Layout
```
output/
├── part_meshes/
│ ├── <part_name>/<mesh_name>.obj # one per direct child Mesh
│ └── ...
└── links/View the complete source on GitHubevo-threejs-obj-export
When your agent uses it
Generates a Node.js ES module script that dynamically imports a Three.js object definition file, constructs a scene graph, applies a -90 deg X-rotation for Y-up to Z-up coordinate conversion (Blender compatibility), forces world matrix updates, serializes the scene to Wavefront OBJ format using OBJExporter, and writes the result to disk.
What it loads into context
Frontmatter
79 tokensAlways available to the agent
SKILL.md
692 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Purpose
- Key Concepts
- Utility Functions
- Direct Execution
Scripts executed separately
scripts/generate_export_script.mjsscripts/run_export.mjs
Files
SKILL.mdcore2,991 bytesSKILL.mdcore2,991 bytesscripts/generate_export_script.mjsruns2,647 bytesscripts/run_export.mjsruns2,426 bytes
Read SKILL.md
# evo-threejs-obj-export
## Purpose
Convert Three.js scene definitions (ES module files exporting geometry constructors) into Wavefront OBJ files suitable for import into Blender (Z-up coordinate system).
## Key Concepts
### Pipeline Steps
1. **Dynamic Import**: Load the Three.js object definition file using `await import(filePath)`
2. **Scene Construction**: Call the exported function (e.g., `createScene()`) to get the 3D object hierarchy
3. **Coordinate Transform**: Apply +90° (Math.PI/2) X-rotation to convert Y-up (Three.js) to Z-up (Blender)
4. **Matrix Baking**: Call `scene.updateMatrixWorld(true)` — CRITICAL in headless Node.js (no renderer to auto-update)
5. **OBJ Export**: Use `OBJExporter.parse(scene)` to serialize to OBJ string
6. **File I/O**: Write the OBJ string to disk with `fs.writeFileSync`View the complete source on GitHubevo-threejs-to-obj
When your agent uses it
Convert Three.js scene graphs to Wavefront OBJ format suitable for Blender (Z-up coordinate system). Handles InstancedMesh, nested hierarchies, coordinate transforms, and headless Node.js execution.
What it loads into context
Frontmatter
50 tokensAlways available to the agent
SKILL.md
836 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Purpose
- Key Domain Knowledge
- Usage
- Files
- Expected Output
- Troubleshooting
Scripts executed separately
scripts/convert.mjs
Files
SKILL.mdcore3,609 bytesSKILL.mdcore3,609 bytesSKILL.mdcore3,609 bytesSKILL.mdcore3,609 bytesscripts/convert.mjsruns11,210 bytes
Read SKILL.md
# evo-threejs-to-obj
## Purpose
Convert Three.js scene graphs to Wavefront OBJ format suitable for Blender (Z-up coordinate system).
## Key Domain Knowledge
### Coordinate System Conversion
- Three.js: Y-up, -Z forward, right-handed
- Blender: Z-up, -Y forward, right-handed
- Apply -90° X rotation: X→X, Y→Z, Z→-Y
- Rotation matrix Rx(-90°): [[1,0,0],[0,0,1],[0,-1,0]]
- Applied AFTER world transform baking, BEFORE writing OBJ
View the complete source on GitHubevo-travel-data-search
When your agent uses it
Query travel CSV datasets with filtering for pet-friendly, cuisine, city, state, budget.
What it loads into context
Frontmatter
28 tokensAlways available to the agent
SKILL.md
155 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Usage
Scripts executed separately
scripts/__init__.pyscripts/search.pyscripts/search_utils.pyscripts/utils.py
Files
SKILL.mdcore666 bytesSKILL.mdcore666 bytesscripts/__init__.pyruns21 bytesscripts/search.pyruns21 bytesscripts/search_utils.pyruns2,602 bytesscripts/utils.pyruns3,520 bytes
Read SKILL.md
# evo-travel-data-search
## Usage
```python
import sys
sys.path.insert(0, '/app/environment/skills/evo-travel-data-search/scripts')
from utils import (search_cities, search_accommodations, search_restaurants,
search_attractions, search_transportation, search_distance)
cities = search_cities('Ohio')
hotels = search_accommodations('Cleveland', pet_friendly=True)
rests = search_restaurants('Cleveland', cuisine='Italian')
attractions = search_attractions('Cleveland')
dist = search_distance('Minneapolis', 'Cleveland')
```View the complete source on GitHubevo-travel-itinerary-builder
When your agent uses it
Assembles 7-day travel itinerary with route optimization, budget validation, and JSON output.
What it loads into context
Frontmatter
30 tokensAlways available to the agent
SKILL.md
154 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Usage
Scripts executed separately
scripts/__init__.pyscripts/utils.py
Files
SKILL.mdcore663 bytesSKILL.mdcore663 bytesscripts/__init__.pyruns21 bytesscripts/utils.pyruns3,969 bytes
Read SKILL.md
# evo-travel-itinerary-builder
## Usage
```python
import sys
sys.path.insert(0, '/app/environment/skills/evo-travel-itinerary-builder/scripts')
from utils import (optimize_route, allocate_days_to_cities, validate_budget,
build_daily_plan, generate_itinerary_json)
route = optimize_route('Minneapolis', ['Cleveland','Columbus','Cincinnati'])
alloc = allocate_days_to_cities(route)
plan, tools = build_daily_plan(alloc, ['American','Mediterranean','Chinese','Italian'])
generate_itinerary_json(plan, tools)
```View the complete source on GitHubevo-travel-planning
When your agent uses it
Build multi-day travel itineraries from structured databases (cities, accommodations, restaurants, attractions, driving distances) with robust constraint validation, budget tracking, and pet-friendly filtering.
What it loads into context
Frontmatter
44 tokensAlways available to the agent
SKILL.md
794 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Purpose
- Key Rules
- Usage
Scripts executed separately
scripts/utils.py
Files
SKILL.mdcore3,343 bytesSKILL.mdcore3,343 bytesscripts/utils.pyruns25,423 bytes
Read SKILL.md
# evo-travel-planning
## Purpose
Build multi-day travel itineraries from structured CSV/text databases covering cities, accommodations, restaurants, attractions, and driving distances. Handles complex constraints including pet-friendly accommodations, cuisine preferences, budget limits, multi-city routing, and transportation restrictions.
## Key Rules
1. All data must come from database files in `/app/data/` — never use LLM memory for POIs.
2. **Pet-friendly accommodations**: `house_rules` column must NOT contain "No pets" (use `na=False` to handle NaN safely per Pandas 2.0.3 best practices).
3. Output accommodation field MUST contain "Pet-friendly" prefix when pet-friendly is required.
4. Cuisine coverage verified from restaurant `Cuisines` field, not restaurant names.
5. All 5 tool names must appear in `tool_called`: `search_cities`, `search_accommodations`, `search_restaurants`, `search_attractions`, `search_driving_distance`.
6. Attractions separated by semicolons with trailing semicolon (e.g., `"Attraction A;Attraction B;"`).
7. Transportation format: `"Self-driving: from A to B"` or `"-"` for same-city days.
8. `current_city`: city name for same-city days, or `"from A to B"` for transit days.View the complete source on GitHubevo-trend-anomaly-causal-inference
When your agent uses it
Complete pipeline for identifying anomalous product category spending patterns in e-commerce data using Prophet counterfactual forecasting, and explaining anomalies through demographic factors via Difference-in-Differences causal inference.
What it loads into context
Frontmatter
50 tokensAlways available to the agent
SKILL.md
731 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Pipeline Steps
- Usage
- Key Design Decisions
- Output Files (saved to /app/output/)
Scripts executed separately
scripts/anomaly_detection.pyscripts/clean_data.pyscripts/feature_engineering.py
Files
SKILL.mdcore3,311 bytesSKILL.mdcore3,311 bytesscripts/anomaly_detection.pyruns5,342 bytesscripts/clean_data.pyruns6,396 bytesscripts/feature_engineering.pyruns3,961 bytes
Read SKILL.md
# Evo Trend Anomaly Causal Inference
Complete pipeline for identifying anomalous product category spending patterns and using DiD causal inference to explain anomalies through demographic factors.
## Pipeline Steps
1. **Data Cleaning** (`scripts/clean_data.py`): Clean survey and purchase data, handling duplicates, missing values, inconsistent formatting, date parsing, monetary columns, and category extraction.
2. **Anomaly Detection** (`scripts/anomaly_detection.py`): Prophet-based counterfactual forecasting to compute deviation index (-100 to 100) per category for March 2020.
3. **Feature Engineering** (`scripts/feature_engineering.py`): One-hot/ordinal encode demographics, bin continuous variables, produce feature-engineered survey CSV.
4. **DiD Analysis** (`scripts/did_analysis.py`): Difference-in-Differences causal analysis for intensive margin (univariate DiD on spend among purchasers) and extensive margin (multivariate heterogeneous DiD on purchase propensity).
## Usage
```pythonView the complete source on GitHubevo-video-filler-word-remover
When your agent uses it
Detects filler words in video/audio interviews using ASR (faster-whisper) with word-level timestamps, saves annotations as JSON, and extracts filler clips into a compilation video.
What it loads into context
Frontmatter
48 tokensAlways available to the agent
SKILL.md
1,051 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Purpose
- Key Concepts
- Filler Words Detected
- Usage
- Pipeline Steps
- Transcription Parameters (Domain-Optimized)
- Duration Estimates
Scripts executed separately
scripts/utils.py
Files
SKILL.mdcore4,176 bytesSKILL.mdcore4,176 bytesscripts/utils.pyruns19,140 bytes
Read SKILL.md
# evo-video-filler-word-remover
## Purpose
Detects filler words and phrases in interview videos using speech recognition (faster-whisper), outputs timestamped annotations as JSON, and stitches all filler word clips into a single compilation video.
## Key Concepts
- Uses **faster-whisper** (CTranslate2-based Whisper) for CPU-optimized transcription
- **`small` model with `int8` quantization**: optimal tradeoff between accuracy and CPU speed (~1GB RAM, 1.5-3x real-time)
- **Word-level timestamps** via DTW cross-attention alignment (~20ms resolution)
- **VAD filter** (Silero) enabled to prevent hallucination on silence
- **`condition_on_previous_text=False`** to prevent the model from skipping disfluencies in favor of grammatically clean output
- **Dual-pass detection**: multi-word phrases first (greedy longest match), then single-word fillers
- **Text normalization**: lowercase, strip punctuation, handle Whisper's leading-space tokenization artifacts
- **Hesitation equivalence**: um, uh, hum, hmm, mhm, umm variants all recognizedView the complete source on GitHubevo-video-tutorial-indexer
When your agent uses it
A comprehensive skill for extracting chapter indices from tutorial videos using FFmpeg audio extraction, OpenAI Whisper ASR transcription with word-level timestamps, and semantic chapter alignment via fuzzy string matching.
What it loads into context
Frontmatter
47 tokensAlways available to the agent
SKILL.md
628 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Workflow
- Key Alignment Principles
- Usage
- Scripts
Scripts executed separately
scripts/chapter_detect.pyscripts/transcribe.pyscripts/utils.py
Files
SKILL.mdcore2,953 bytesSKILL.mdcore2,953 bytesscripts/chapter_detect.pyruns15,089 bytesscripts/transcribe.pyruns6,207 bytesscripts/utils.pyruns2,014 bytes
Read SKILL.md
# evo-video-tutorial-indexer
A comprehensive skill for extracting chapter indices from tutorial videos using
FFmpeg audio extraction, OpenAI Whisper ASR transcription with word-level timestamps,
and semantic chapter alignment via fuzzy string matching.
## Workflow
1. **Extract** audio from MP4 using FFmpeg (16kHz mono PCM WAV for optimal Whisper input)
2. **Transcribe** the audio using OpenAI Whisper with word-level timestamps enabled
3. **Analyze** transcript words using sliding window fuzzy matching to locate chapter boundaries
4. **Align** chapter titles to timestamps using multiple matching strategies and keyword heuristics
5. **Validate** structural requirements (monotonic timestamps, correct count, within duration)
6. **Output** JSON with video_info and chapters arrayView the complete source on GitHubevo-pddl-plan-formatter
When your agent uses it
Handles plan output formatting and end-to-end task orchestration. Reads problem.json, calls the solver for each task, formats plans in action_name(param1, param2, ...) syntax, and writes output files.
What it loads into context
Frontmatter
53 tokensAlways available to the agent
SKILL.md
365 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Key Functions
- Usage
- Output Format
- Dependencies
- Notes
Scripts executed separately
scripts/utils.py
Files
SKILL.mdcore1,474 bytesSKILL.mdcore1,474 bytesscripts/utils.pyruns3,592 bytes
Read SKILL.md
# evo-pddl-plan-formatter
Orchestrates solving of all PDDL tasks from problem.json and writes
correctly formatted plan output files.
## Key Functions
- `run_all_tasks(problem_json_path, base_dir=None)` - Main orchestrator
- `write_plan_custom_format(plan_actions, filename)` - Write action_name(p1, p2) format
- `write_plan_pddl_format(plan_actions, filename)` - Write (action_name p1 p2) format
- `format_action_instance(action_name, params)` - Format single action
## Usage
View the complete source on GitHubevo-pddl-solver
When your agent uses it
Core PDDL planning solver that parses domain/problem files, invokes pyperplan with optimal search configuration (GBFS + hFF), handles timeouts and fallbacks, and returns a plan as a list of action strings.
What it loads into context
Frontmatter
54 tokensAlways available to the agent
SKILL.md
428 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Key Functions
- Usage
- Strategy
- Airport Domain Notes
Scripts executed separately
scripts/utils.py
Files
SKILL.mdcore1,714 bytesSKILL.mdcore1,714 bytesscripts/utils.pyruns5,804 bytes
Read SKILL.md
# evo-pddl-solver
Solves PDDL planning problems using unified_planning with pyperplan backend,
with direct pyperplan fallback.
## Key Functions
- `solve_pddl_task(domain_path, problem_path, timeout=300)` - Main entry point
- `solve_with_unified_planning(domain_path, problem_path, timeout=300)` - UP-based solving
- `solve_with_pyperplan_direct(domain_path, problem_path, timeout=300)` - Direct pyperplan
- `solve_with_fallback_strategies(domain_path, problem_path, timeout=300)` - Try all strategies
## Usage
View the complete source on GitHubevo-virtualhome-agent-planning
When your agent uses it
Solves PDDL airport ground traffic control planning problems from the IPC Airport domain. Uses unified-planning with pyperplan backend (GBFS + hFF for agile solving), with direct pyperplan fallback, robust timeout/memout handling, and correct plan output formatting.
What it loads into context
Frontmatter
67 tokensAlways available to the agent
SKILL.md
627 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Description
- Key Domain Knowledge
- Dependencies
- Usage
- Functions
Scripts executed separately
scripts/solver.py
Files
SKILL.mdcore2,639 bytesSKILL.mdcore2,639 bytesscripts/solver.pyruns17,762 bytes
Read SKILL.md
# evo-virtualhome-agent-planning
## Description
Solves PDDL airport ground traffic control planning problems from the IPC Airport domain.
Uses unified-planning with pyperplan backend to automatically find valid plans, with multiple
fallback strategies and robust error handling for large-scale instances (up to Munich Airport scale).
## Key Domain Knowledge
- Airport domain models ground traffic: airplanes taxi between segments (taxiways, runways, parking)
- Actions: move, startup (pushing->moving), park (terminal), takeoff (terminal), pushback
- Dual-predicate pattern: occupied/not_occupied, blocked/not_blocked must be maintained
- Blocking is per-airplane (safety buffers)
- IPC-4 Airport domain is PSPACE-hard; largest instances encode full Munich Airport (MUC)
- STRIPS-compiled versions required for pyperplan (no ADL/negative preconditions support)View the complete source on GitHubevo-excel-gcc-net-exports-formulas
When your agent uses it
Generate workbook-specific INDEX/MATCH lookup formulas and downstream GCC net-exports formulas for the target workbook layout.
What it loads into context
Frontmatter
36 tokensAlways available to the agent
SKILL.md
320 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
Scripts executed separately
scripts/utils.py
Files
SKILL.mdcore1,265 bytesscripts/utils.pyruns3,152 bytes
Read SKILL.md
This skill handles workbook-specific financial/statistical formula construction.
Knowledge internalized:
- The lookup blocks H12:L17, H19:L24, and H26:L31 must contain formulas, not pasted values.
- For this workbook, stable lookup formulas are built with `INDEX` on the exact Data row for each series and `MATCH` on the year header in `Data!I4:M4` against the Task year cells in row 9.
- Net exports percent of GDP is `(exports - imports) / GDP` with blank/zero guard.
- Summary rows are MIN row 43, MAX row 44, MEDIAN row 45, AVERAGE row 46, 25th percentile row 47, 75th percentile row 48.
- Percentiles must use `PERCENTILE.INC`, not legacy `PERCENTILE`.
- GCC weighted mean is on row 50 and uses `SUMPRODUCT(ratios, GDPs)/SUM(GDPs)`.
- Formula strings must be English and comma-separated.
Functions:
- `map_task_ranges()`
- `build_two_key_lookup_formula(task_row, year_col)`View the complete source on GitHubevo-excel-workbook-formula-io
When your agent uses it
Load existing workbooks with openpyxl, validate required sheets and ranges, write Excel formulas into existing cells, save safely, and trigger headless recalculation while preserving formatting.
What it loads into context
Frontmatter
49 tokensAlways available to the agent
SKILL.md
410 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
Scripts executed separately
scripts/utils.py
Files
SKILL.mdcore1,831 bytesSKILL.mdcore1,831 bytesscripts/utils.pyruns8,333 bytes
Read SKILL.md
This skill handles workbook I/O and formula injection only.
Knowledge internalized:
- Use `openpyxl.load_workbook(filename=..., read_only=False, data_only=False, keep_vba=False, keep_links=True)` for editable `.xlsx` workbooks.
- Access sheets with `wb['Task']` style, not deprecated APIs.
- Write formulas as English Excel formulas beginning with `=` and using comma separators.
- Preserve workbook structure by modifying only existing sheets/cells; do not create/remove sheets.
- `openpyxl` does not calculate formulas; for reliable cached values on Linux, start LibreOffice headless with a UNO socket, open the workbook, call `calculateAll()`, and save/close it. Use plain `--convert-to` only as fallback.
- Validation should confirm required sheets exist before writing.
- When multiple skills have `utils.py`, use importlib file-based loading to avoid module-name collisions.
Functions:
- `load_editable_workbook(path)`
- `load_cached_workbook(path)`View the complete source on GitHubevo-excel-io
When your agent uses it
Provides utility functions for loading, scanning, and saving Excel workbooks with openpyxl 3.1.5, including handling merged cells, detecting placeholder markers, and preserving formatting when writing numeric values back.
What it loads into context
Frontmatter
52 tokensAlways available to the agent
SKILL.md
483 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Key Features
- Usage
- Functions
Scripts executed separately
scripts/excel_io.pyscripts/utils.py
Files
SKILL.mdcore1,925 bytesSKILL.mdcore1,925 bytesscripts/excel_io.pyruns4,354 bytesscripts/utils.pyruns4,354 bytes
Read SKILL.md
# evo-excel-io
Utility functions for safe Excel I/O with openpyxl 3.1.5.
## Key Features
- Monkey-patches openpyxl 3.1.5 AppVersion bug to prevent chart corruption
- Safe cell value reading that handles MergedCell objects
- Scanning all sheets for "???" placeholder markers
- Writing recovered numeric values with proper type casting
- Preserving cell formatting during value replacement
## Usage
```pythonView the complete source on GitHubevo-nasa-budget-recovery
When your agent uses it
Analyzes NASA budget workbook mathematical structure to recover missing ??? values via constraint propagation across sheets (row sums, YoY percentages, directorate shares, growth analysis).
What it loads into context
Frontmatter
44 tokensAlways available to the agent
SKILL.md
348 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Relationships Detected
- Usage
- Key Functions
Scripts executed separately
scripts/utils.py
Files
SKILL.mdcore1,374 bytesSKILL.mdcore1,374 bytesscripts/utils.pyruns7,232 bytes
Read SKILL.md
# evo-nasa-budget-recovery
Recovers missing ??? values in multi-sheet NASA budget Excel files.
## Relationships Detected
1. **Row sums**: Budget sheet Total col = sum of directorate cols
2. **YoY %**: (current - previous) / previous * 100, rounded to 2 decimals
3. **Shares %**: directorate_val / total * 100, rounded to 2 decimals
4. **Growth Analysis**: CAGR, 5-year change, average annual budget
5. **Cross-sheet**: Budget values recoverable from YoY + previous year
## Usage
```pythonView the complete source on GitHubevo-xlsx-recover-data
When your agent uses it
Recover missing values (marked as "???") in a multi-sheet NASA budget Excel workbook. Handles 4 interdependent sheets with cross-sheet constraint propagation, floating-point precision management, and robust Excel I/O via openpyxl.
What it loads into context
Frontmatter
57 tokensAlways available to the agent
SKILL.md
824 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Purpose
- Key Formulas
- Rounding Rules
- Sheet Layout Details
- Dependency Resolution Strategy
- Robustness Features
- Usage
Files
SKILL.mdcore2,998 bytesSKILL.mdcore2,998 bytes
Read SKILL.md
# evo-xlsx-recover-data
## Purpose
Recover missing values (marked as "???") in a multi-sheet NASA budget Excel workbook.
The workbook has 4 interdependent sheets:
1. **Budget by Directorate** - Raw dollar values ($M) per category per year (FY2015-FY2024)
2. **YoY Changes (%)** - Year-over-year percentage changes
3. **Directorate Shares (%)** - Each category as % of yearly total
4. **Growth Analysis** - Summary statistics (CAGR, averages, deltas) for FY2019-2024
## Key Formulas
- **Row Sum**: Total = sum of all category columns
- **YoY%**: ((current - previous) / previous) * 100, rounded to 2dp
- **Share%**: (category / total) * 100, rounded to 2dpView the complete source on GitHubSkills included
- evo-3d-scan-calc
- evo-mass-report-output
- evo-mesh-geometry-analysis
- evo-stl-binary-parser
- evo-adaptive-cruise-control
- evo-azure-bgp-oscillation-route-leak
- evo-bibtex-parser
- evo-citation-scorer
- evo-citation-verifier
- evo-civ6-adjacency-rules
- evo-civ6-map-parser
- evo-civ6-placement-optimizer
- evo-pdf-field-inspector
- evo-pdf-form-filler
- evo-crystallography-fraction-format
- evo-crystallography-wyckoff-analysis
- evo-network-stats-computation
- evo-pcap-feature-extraction
- evo-d3v6-stock-visualization
- evo-web-scaffold-generator
- evo-dialogue-dotgen
- evo-dialogue-output
- evo-dialogue-parser
- evo-egomotion-dynamic-analysis
- evo-output-serialization
- evo-video-sampling
- evo-seismic-data-io
- evo-seismic-phase-association
- evo-seismic-phase-picking
- evo-geospatial-antimeridian-plates
- evo-geospatial-earthquake-distance
- evo-macro-cycle-correlation
- evo-macro-data-ingestion
- evo-acopf-network-parser
- evo-acopf-report-generator
- evo-acopf-solver
- evo-dcopf-solver
- evo-market-report
- evo-matpower-parser
- evo-enterprise-doc-parser
- evo-enterprise-qa-pipeline
- evo-pptx-embedded-excel-updater
- evo-tess-lightcurve-preprocessing
- evo-transit-period-detection
- evo-excel-match-analyzer
- evo-pdf-context-extractor
- evo-build-diagnosis
- evo-patch-generate-apply
- evo-maven-build-diagnosis
- evo-maven-patch-generation
- evo-druid-cve-patch
- evo-erlang-ssh-cve-patch
- evo-flink-session-job
- evo-flood-risk-analysis
- evo-usgs-flood-detection
- evo-gh-data-fetcher
- evo-gh-report-generator
- evo-glm-simulation
- evo-gw-grid-search-output
- evo-gw-matched-filter-engine
- evo-grid-dispatch-operator
- evo-thermal-pid-control
- evo-thermal-sysid
- evo-invoice-fraud-detector
- evo-pdf-invoice-parser
- evo-reference-data-loader
- evo-jax-compute
- evo-jax-computing-basics
- evo-jax-io
- evo-ocr-preprocess-extract
- evo-receipt-parse-export
- evo-clinical-data-cleaning
- evo-clinical-unit-harmonization
- evo-lake-data-pipeline
- evo-lake-factor-attribution
- evo-lake-trend-analysis
- evo-latex-formula-extraction
- evo-latex-syntax-validation
- evo-pdf-to-markdown
- evo-lean4-recursive-sequence-inequality-proof
- evo-defect-pipeline
- evo-fuzzy-match
- evo-text-normalize
- evo-reflow-handbook-parser
- evo-reflow-json-output
- evo-reflow-thermal-analysis
- evo-fjsp-data-io
- evo-fjsp-scheduler
- evo-fjsp-validator
- evo-template-matching-counter
- evo-video-keyframe-extraction
- evo-mars-clustering-eval
- evo-mars-grid-search
- evo-mars-pareto-output
- evo-dubbing-audio-processing
- evo-dubbing-mux-report
- evo-dubbing-tts-synthesis
- evo-docx-template-filler
- evo-document-classify-and-sort
- evo-document-text-extraction
- evo-pdf-content-extraction
- evo-pdf-redaction-engine
- evo-parallel-batch-search
- evo-parallel-determinism
- evo-parallel-index-building
- evo-tpp-solver
- evo-dataframe-diff-report
- evo-pdf-excel-extraction
- evo-pedestrian-vlm-counting
- evo-video-frame-extraction
- evo-tts-audiobook-synth
- evo-web-essay-scraper
- evo-openpyxl-sheet-processor
- evo-powerlifting-dots-formula
- evo-pptx-reference-slide
- evo-pptx-title-detect-format
- evo-pptx-xml-io
- evo-protein-expression-analysis
- evo-proteomics-excel-formulas
- evo-scala-idiom-mapping
- evo-scala-tokenizer-generator
- evo-dicke-model-simulation
- evo-wigner-csv-export
- evo-r2r-linearization
- evo-r2r-mpc-controller
- evo-nextjs-api-optimization
- evo-nextjs-bundle-reduction
- evo-nextjs-render-optimization
- evo-excel-data-extraction
- evo-excel-financial-formulas
- evo-sales-pivot-analysis
- evo-sec13f-analyzer
- evo-seismic-data-preprocessing
- evo-seismic-phase-picking
- evo-atheris-fuzz-driver
- evo-fuzz-env-runner
- evo-python-library-discovery
- evo-macro-demand-shock-scenarios
- evo-macro-sut-import-share
- evo-macro-weo-data
- evo-simpo-code-reproduction
- evo-software-dependency-audit
- evo-speaker-diarization-subtitles
- evo-spring-boot-jakarta-migration
- evo-suricata-custom-exfil
- evo-syzkaller-ppdev-syzlang
- evo-cluster-naming
- evo-semantic-hierarchical-clustering
- evo-taxonomy-data-pipeline
- evo-threejs-scene-parser
- evo-threejs-obj-export
- evo-threejs-to-obj
- evo-travel-data-search
- evo-travel-itinerary-builder
- evo-travel-planning
- evo-trend-anomaly-causal-inference
- evo-video-filler-word-remover
- evo-video-tutorial-indexer
- evo-pddl-plan-formatter
- evo-pddl-solver
- evo-virtualhome-agent-planning
- evo-excel-gcc-net-exports-formulas
- evo-excel-workbook-formula-io
- evo-excel-io
- evo-nasa-budget-recovery
- evo-xlsx-recover-data
Repository facts
- License
- Apache-2.0
- Created
- Jun 3, 2026
- Last pushed
- Sep 10, 2026
- Forks
- 4
- Open issues
- 3
- Project activity
- Active
Before you install
Network or broad shellAutomated signals, not a guarantee
Checked Nov 6, 2026
Not fully analyzed: some files were too long, unreadable or missing. This never lowers the level.
Show 203 notes
tasks-evolved/3d-scan-calc/environment/skills/evo-3d-scan-calc/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedtasks-evolved/3d-scan-calc/environment/skills/evo-3d-scan-calc/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedtasks-evolved/3d-scan-calc/environment/skills/evo-mass-report-output/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedtasks-evolved/3d-scan-calc/environment/skills/evo-mesh-geometry-analysis/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedtasks-evolved/3d-scan-calc/environment/skills/evo-stl-binary-parser/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedtasks-evolved/adaptive-cruise-control/environment/skills/evo-adaptive-cruise-control/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedtasks-evolved/adaptive-cruise-control/environment/skills/evo-adaptive-cruise-control/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedtasks-evolved/adaptive-cruise-control/environment/skills/evo-adaptive-cruise-control/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedtasks-evolved/adaptive-cruise-control/environment/skills/evo-adaptive-cruise-control/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedtasks-evolved/azure-bgp-oscillation-route-leak/environment/skills/evo-azure-bgp-oscillation-route-leak/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedtasks-evolved/citation-check/environment/skills/evo-bibtex-parser/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedtasks-evolved/citation-check/environment/skills/evo-citation-scorer/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedtasks-evolved/citation-check/environment/skills/evo-citation-verifier/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedtasks-evolved/civ6-adjacency-optimizer/environment/skills/evo-civ6-adjacency-rules/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedtasks-evolved/civ6-adjacency-optimizer/environment/skills/evo-civ6-map-parser/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedtasks-evolved/civ6-adjacency-optimizer/environment/skills/evo-civ6-placement-optimizer/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedtasks-evolved/court-form-filling/environment/skills/evo-pdf-field-inspector/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedtasks-evolved/court-form-filling/environment/skills/evo-pdf-form-filler/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedtasks-evolved/crystallographic-wyckoff-position-analysis/environment/skills/evo-crystallography-fraction-format/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedtasks-evolved/crystallographic-wyckoff-position-analysis/environment/skills/evo-crystallography-wyckoff-analysis/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzed
- No broad tool permissions
- No dangerous shell commands
- 101 network referencesin 20 files: evo-excel-workbook-formula-io/scripts/utils.py:42 evo-gh-data-fetcher/scripts/utils.py:19 evo-proteomics-excel-formulas/scripts/utils.py:66 and 17 more
- 2 obfuscation signalsin 2 files: evo-pdf-invoice-parser/scripts/utils.py:21 evo-pedestrian-vlm-counting/scripts/pedestrian_counting.py:173
- No instruction overrides
- 205 executable scriptsin 205 files: evo-3d-scan-calc/scripts/utils.py:1 evo-mass-report-output/scripts/utils.py:1 evo-mesh-geometry-analysis/scripts/utils.py:1 and 202 more
- 18 references to secretsin 6 files: evo-pedestrian-vlm-counting/scripts/pedestrian_counting.py:94 evo-tts-audiobook-synth/scripts/utils.py:12 evo-acopf-solver/scripts/utils.py:9 and 3 more
- No requests to vote in Hot
Show all 326 signals by file
tasks-evolved/3d-scan-calc/environment/skills/evo-3d-scan-calc/scripts/utils.py
- Executable scriptline 1
Executable file
tasks-evolved/3d-scan-calc/environment/skills/evo-mass-report-output/scripts/utils.py
- Executable scriptline 1
Executable file
tasks-evolved/3d-scan-calc/environment/skills/evo-mesh-geometry-analysis/scripts/utils.py
- Executable scriptline 1
Executable file
tasks-evolved/3d-scan-calc/environment/skills/evo-stl-binary-parser/scripts/utils.py
- Executable scriptline 1
Executable file
tasks-evolved/adaptive-cruise-control/environment/skills/evo-adaptive-cruise-control/scripts/acc_system.py
- Executable scriptline 1
Executable file
tasks-evolved/adaptive-cruise-control/environment/skills/evo-adaptive-cruise-control/scripts/pid_controller.py
- Executable scriptline 1
Executable file
tasks-evolved/adaptive-cruise-control/environment/skills/evo-adaptive-cruise-control/scripts/simulation.py
- Executable scriptline 1
Executable file
tasks-evolved/adaptive-cruise-control/environment/skills/evo-adaptive-cruise-control/scripts/tuning.py
- Executable scriptline 1
Executable file
tasks-evolved/azure-bgp-oscillation-route-leak/environment/skills/evo-azure-bgp-oscillation-route-leak/scripts/utils.py
- Executable scriptline 1
Executable file
tasks-evolved/citation-check/environment/skills/evo-bibtex-parser/scripts/utils.py
- Executable scriptline 1
Executable file
tasks-evolved/citation-check/environment/skills/evo-citation-scorer/scripts/utils.py
- Executable scriptline 1
Executable file
tasks-evolved/citation-check/environment/skills/evo-citation-verifier/scripts/utils.py
- Executable scriptline 1
Executable file - Network accessline 19
session = requests.Session() - Network accessline 58
url = f"https://api.crossref.org/works/{doi}" - Network accessline 97
data = rate_limited_query(session, "https://api.crossref.org/works", params) - Network accessline 129
data = rate_limited_query(session, "https://api.semanticscholar.org/graph/v1/paper/search", params, delay=3.0) - Network accessline 159
data = rate_limited_query(session, "https://dblp.org/search/publ/api", params)
tasks-evolved/civ6-adjacency-optimizer/environment/skills/evo-civ6-adjacency-rules/scripts/utils.py
- Executable scriptline 1
Executable file
tasks-evolved/civ6-adjacency-optimizer/environment/skills/evo-civ6-map-parser/scripts/utils.py
- Executable scriptline 1
Executable file
tasks-evolved/civ6-adjacency-optimizer/environment/skills/evo-civ6-placement-optimizer/scripts/utils.py
- Executable scriptline 1
Executable file
tasks-evolved/court-form-filling/environment/skills/evo-pdf-field-inspector/scripts/utils.py
- Executable scriptline 1
Executable file
tasks-evolved/court-form-filling/environment/skills/evo-pdf-form-filler/scripts/utils.py
- Executable scriptline 1
Executable file
tasks-evolved/crystallographic-wyckoff-position-analysis/environment/skills/evo-crystallography-fraction-format/scripts/fraction_utils.py
- Executable scriptline 1
Executable file
tasks-evolved/crystallographic-wyckoff-position-analysis/environment/skills/evo-crystallography-wyckoff-analysis/scripts/utils.py
- Executable scriptline 1
Executable file
tasks-evolved/dapt-intrusion-detection/environment/skills/evo-network-stats-computation/scripts/utils.py
- Executable scriptline 1
Executable file
tasks-evolved/dapt-intrusion-detection/environment/skills/evo-pcap-feature-extraction/scripts/utils.py
- Executable scriptline 1
Executable file
tasks-evolved/data-to-d3/environment/skills/evo-d3v6-stock-visualization/scripts/utils.py
- Executable scriptline 1
Executable file
tasks-evolved/data-to-d3/environment/skills/evo-web-scaffold-generator/scripts/utils.py
- Executable scriptline 1
Executable file - Network accessline 35
try: subprocess.run( ['curl', '-s', '--max-time', '30', 'https://d3js.org/d3.v6.min.js', '-o', d3_path], - Network accessline 36
subprocess.run( ['curl', '-s', '--max-time', '30', 'https://d3js.org/d3.v6.min.js', '-o', d3_path], check=True - Network accessline 37
['curl', '-s', '--max-time', '30', 'https://d3js.org/d3.v6.min.js', '-o', d3_path],
tasks-evolved/dialogue-parser/environment/skills/evo-dialogue-dotgen/scripts/dotgen_utils.py
- Executable scriptline 1
Executable file
tasks-evolved/dialogue-parser/environment/skills/evo-dialogue-output/scripts/__init__.py
- Executable scriptline 1
Executable file
tasks-evolved/dialogue-parser/environment/skills/evo-dialogue-output/scripts/utils.py
- Executable scriptline 1
Executable file
tasks-evolved/dialogue-parser/environment/skills/evo-dialogue-parser/scripts/__init__.py
- Executable scriptline 1
Executable file
tasks-evolved/dialogue-parser/environment/skills/evo-dialogue-parser/scripts/utils.py
- Executable scriptline 1
Executable file
tasks-evolved/dynamic-object-aware-egomotion/environment/skills/evo-egomotion-dynamic-analysis/scripts/utils.py
- Executable scriptline 1
Executable file
tasks-evolved/dynamic-object-aware-egomotion/environment/skills/evo-output-serialization/scripts/utils.py
- Executable scriptline 1
Executable file
tasks-evolved/dynamic-object-aware-egomotion/environment/skills/evo-video-sampling/scripts/utils.py
- Executable scriptline 1
Executable file
tasks-evolved/earthquake-phase-association/environment/skills/evo-seismic-data-io/scripts/utils.py
- Executable scriptline 1
Executable file
tasks-evolved/earthquake-phase-association/environment/skills/evo-seismic-phase-association/scripts/utils.py
- Executable scriptline 1
Executable file
tasks-evolved/earthquake-phase-association/environment/skills/evo-seismic-phase-picking/scripts/utils.py
- Executable scriptline 1
Executable file
tasks-evolved/earthquake-plate-calculation/environment/skills/evo-geospatial-antimeridian-plates/scripts/utils.py
- Executable scriptline 1
Executable file
tasks-evolved/earthquake-plate-calculation/environment/skills/evo-geospatial-earthquake-distance/scripts/utils.py
- Executable scriptline 1
Executable file
tasks-evolved/econ-detrending-correlation/environment/skills/evo-macro-cycle-correlation/scripts/utils.py
- Executable scriptline 1
Executable file
tasks-evolved/econ-detrending-correlation/environment/skills/evo-macro-data-ingestion/scripts/data_ingestion.py
- Executable scriptline 1
Executable file
tasks-evolved/econ-detrending-correlation/environment/skills/evo-macro-data-ingestion/scripts/utils.py
- Executable scriptline 1
Executable file
tasks-evolved/energy-ac-optimal-power-flow/environment/skills/evo-acopf-network-parser/scripts/utils.py
- Executable scriptline 1
Executable file
tasks-evolved/energy-ac-optimal-power-flow/environment/skills/evo-acopf-report-generator/scripts/utils.py
- Executable scriptline 1
Executable file
tasks-evolved/energy-ac-optimal-power-flow/environment/skills/evo-acopf-solver/scripts/utils.py
tasks-evolved/energy-market-pricing/environment/skills/evo-dcopf-solver/scripts/utils.py
- Executable scriptline 1
Executable file
tasks-evolved/energy-market-pricing/environment/skills/evo-market-report/scripts/utils.py
- Executable scriptline 1
Executable file
tasks-evolved/energy-market-pricing/environment/skills/evo-matpower-parser/scripts/utils.py
- Executable scriptline 1
Executable file
tasks-evolved/enterprise-information-search/environment/skills/evo-enterprise-doc-parser/scripts/utils.py
- Executable scriptline 1
Executable file
tasks-evolved/enterprise-information-search/environment/skills/evo-enterprise-qa-pipeline/scripts/utils.py
- Executable scriptline 1
Executable file
tasks-evolved/exceltable-in-ppt/environment/skills/evo-pptx-embedded-excel-updater/scripts/utils.py
- Executable scriptline 1
Executable file - Network accessline 44
if ole_obj_list: ole_obj = ole_obj_list[0] r_id = ole_obj.get('{http://schemas.openxmlformats.org/officeDocument/2006/relationships}id') - Network accessline 45
ole_obj = ole_obj_list[0] r_id = ole_obj.get('{http://schemas.openxmlformats.org/officeDocument/2006/relationships}id') if r_id: - Network accessline 46
r_id = ole_obj.get('{http://schemas.openxmlformats.org/officeDocument/2006/relationships}id')
tasks-evolved/exoplanet-detection-period/environment/skills/evo-tess-lightcurve-preprocessing/scripts/utils.py
- Executable scriptline 1
Executable file
tasks-evolved/exoplanet-detection-period/environment/skills/evo-transit-period-detection/scripts/utils.py
- Executable scriptline 1
Executable file
tasks-evolved/financial-modeling-qa/environment/skills/evo-excel-match-analyzer/scripts/utils.py
- Executable scriptline 1
Executable file
tasks-evolved/financial-modeling-qa/environment/skills/evo-pdf-context-extractor/scripts/utils.py
- Executable scriptline 1
Executable file
tasks-evolved/find-topk-similiar-chemicals/environment/skills/evo-molecule-similarity/scripts/utils.py
- Executable scriptline 1
Executable file
tasks-evolved/fix-build-agentops/environment/skills/evo-build-diagnosis/scripts/diagnosis.py
- Executable scriptline 1
Executable file
tasks-evolved/fix-build-agentops/environment/skills/evo-patch-generate-apply/scripts/patch.py
- Executable scriptline 1
Executable file
tasks-evolved/fix-build-agentops/environment/skills/evo-python-build-fixer/scripts/utils.py
- Executable scriptline 1
Executable file
tasks-evolved/fix-build-google-auto/environment/skills/evo-maven-build-diagnosis/scripts/utils.py
tasks-evolved/fix-build-google-auto/environment/skills/evo-maven-patch-generation/scripts/utils.py
- Executable scriptline 1
Executable file
tasks-evolved/fix-druid-loophole-cve/environment/skills/evo-druid-cve-patch/scripts/patch_druid.py
- Executable scriptline 1
Executable file - Network accessline 21
lines.append(' * with the License. You may obtain a copy of the License at') lines.append(' *') lines.append(' * http://www.apache.org/licenses/LICENSE-2.0') - Network accessline 22
lines.append(' *') lines.append(' * http://www.apache.org/licenses/LICENSE-2.0') lines.append(' *') - Network accessline 23
lines.append(' * http://www.apache.org/licenses/LICENSE-2.0') - Access to secretsline 163
[Credential-related source omitted]
tasks-evolved/fix-erlang-ssh-cve/environment/skills/evo-erlang-ssh-cve-patch/scripts/patch_ssh_connection.py
- Executable scriptline 1
Executable file
tasks-evolved/fix-erlang-ssh-cve/environment/skills/evo-erlang-ssh-cve-patch/scripts/run_patch.py
- Executable scriptline 1
#!/usr/bin/env python3
tasks-evolved/fix-erlang-ssh-cve/environment/skills/evo-erlang-ssh-cve-patch/scripts/utils.py
- Executable scriptline 1
Executable file
tasks-evolved/flink-query/environment/skills/evo-flink-session-job/scripts/generate_java.py
- Executable scriptline 1
#!/usr/bin/env python3
tasks-evolved/flood-risk-analysis/environment/skills/evo-flood-risk-analysis/SKILL.md
- Network accessline 12
1. **Gage height (parameter 00065)** is used — NOT discharge (00060). 2. **Daily maximum of instantaneous (15-min) readings** is the aggregation method. Use `nwis.get_iv()` to fetch instantaneous values, then resample to daily max with `.re - Network accessline 13
2. **Daily maximum of instantaneous (15-min) readings** is the aggregation method. Use `nwis.get_iv()` to fetch instantaneous values, then resample to daily max with `.resample('D').max()`. 3. **NWS flood stage thresholds** come from the NW - Network accessline 14
3. **NWS flood stage thresholds** come from the NWS All Gauges Report CSV at `https://water.noaa.gov/resources/downloads/reports/nwps_all_gauges_report.csv`. Match stations by USGS site ID (`usgs_id` or `gaugelid` column). The flood stage c
tasks-evolved/flood-risk-analysis/environment/skills/evo-flood-risk-analysis/scripts/utils.py
- Executable scriptline 1
Executable file - Network accessline 54
url = 'https://water.noaa.gov/resources/downloads/reports/nwps_all_gauges_report.csv' - Network accessline 62
import urllib.request import io req = urllib.request.Request(url, headers={'User-Agent': 'Mozilla/5.0'}) - Network accessline 63
import io req = urllib.request.Request(url, headers={'User-Agent': 'Mozilla/5.0'}) response = urllib.request.urlopen(req, timeout=60) - Network accessline 64
req = urllib.request.Request(url, headers={'User-Agent': 'Mozilla/5.0'}) - Network accessline 65
response = urllib.request.urlopen(req, timeout=60)
tasks-evolved/flood-risk-analysis/environment/skills/evo-usgs-flood-detection/scripts/__init__.py
- Executable scriptline 1
Executable file
tasks-evolved/flood-risk-analysis/environment/skills/evo-usgs-flood-detection/scripts/utils.py
- Executable scriptline 1
Executable file
tasks-evolved/gh-repo-analytics/environment/skills/evo-gh-data-fetcher/SKILL.md
- Network accessline 8
Fetches PR and issue data from GitHub repositories using the GitHub REST API (via curl subprocess calls). Works without gh CLI authentication by using unauthenticated API access for public repos. - Network accessline 40
- `parse_gh_timestamp(ts_string)` - Parse ISO 8601 GitHub timestamp to datetime - `run_github_api(url)` - Execute curl to GitHub REST API, return parsed JSON - Network accessline 41
- `run_github_api(url)` - Execute curl to GitHub REST API, return parsed JSON
tasks-evolved/gh-repo-analytics/environment/skills/evo-gh-data-fetcher/scripts/fetch.py
- Executable scriptline 1
Executable file
tasks-evolved/gh-repo-analytics/environment/skills/evo-gh-data-fetcher/scripts/utils.py
- Executable scriptline 1
Executable file - Network accessline 19
"""Execute a curl command to GitHub REST API and return parsed JSON.""" - Network accessline 32
page = 1 while page <= max_pages: url = f"https://api.github.com/search/issues?q={query}&per_page={per_page}&page={page}" - Network accessline 33
while page <= max_pages: url = f"https://api.github.com/search/issues?q={query}&per_page={per_page}&page={page}" data = run_github_api(url) - Network accessline 34
url = f"https://api.github.com/search/issues?q={query}&per_page={per_page}&page={page}" - Network accessline 59
pr_url = f"https://api.github.com/repos/{repo}/pulls/{pr_number}" - Network accessline 78
enriched = [] for i, num in enumerate(pr_numbers): pr_url = f"https://api.github.com/repos/{repo}/pulls/{num}" - Network accessline 79
for i, num in enumerate(pr_numbers): pr_url = f"https://api.github.com/repos/{repo}/pulls/{num}" pr_detail = run_github_api(pr_url) - Network accessline 80
pr_url = f"https://api.github.com/repos/{repo}/pulls/{num}"
tasks-evolved/gh-repo-analytics/environment/skills/evo-gh-report-generator/scripts/report.py
- Executable scriptline 1
Executable file
tasks-evolved/gh-repo-analytics/environment/skills/evo-gh-report-generator/scripts/utils.py
- Executable scriptline 1
Executable file
tasks-evolved/glm-lake-mendota/environment/skills/evo-glm-simulation/scripts/utils.py
tasks-evolved/gravitational-wave-detection/environment/skills/evo-gw-grid-search-output/scripts/grid_utils.py
- Executable scriptline 1
Executable file
tasks-evolved/gravitational-wave-detection/environment/skills/evo-gw-matched-filter-engine/scripts/engine_utils.py
- Executable scriptline 1
Executable file
tasks-evolved/grid-dispatch-operator/environment/skills/evo-grid-dispatch-operator/scripts/data_loader.py
- Executable scriptline 1
Executable file
tasks-evolved/grid-dispatch-operator/environment/skills/evo-grid-dispatch-operator/scripts/network_model.py
- Executable scriptline 1
Executable file
tasks-evolved/grid-dispatch-operator/environment/skills/evo-grid-dispatch-operator/scripts/optimizer.py
- Executable scriptline 1
Executable file
tasks-evolved/grid-dispatch-operator/environment/skills/evo-grid-dispatch-operator/scripts/report_generator.py
- Executable scriptline 1
Executable file
tasks-evolved/grid-dispatch-operator/environment/skills/evo-grid-dispatch-operator/scripts/solve.py
- Executable scriptline 1
Executable file
tasks-evolved/hvac-control/environment/skills/evo-thermal-pid-control/scripts/pid_utils.py
- Executable scriptline 1
Executable file
tasks-evolved/hvac-control/environment/skills/evo-thermal-pid-control/scripts/utils.py
- Executable scriptline 1
Executable file
tasks-evolved/hvac-control/environment/skills/evo-thermal-sysid/scripts/sysid_utils.py
- Executable scriptline 1
Executable file
tasks-evolved/hvac-control/environment/skills/evo-thermal-sysid/scripts/utils.py
- Executable scriptline 1
Executable file
tasks-evolved/invoice-fraud-detection/environment/skills/evo-invoice-fraud-detector/scripts/utils.py
- Executable scriptline 1
Executable file
tasks-evolved/invoice-fraud-detection/environment/skills/evo-pdf-invoice-parser/scripts/utils.py
tasks-evolved/invoice-fraud-detection/environment/skills/evo-reference-data-loader/scripts/utils.py
- Executable scriptline 1
Executable file
tasks-evolved/jax-computing-basics/environment/skills/evo-jax-compute/scripts/__init__.py
- Executable scriptline 1
Executable file
tasks-evolved/jax-computing-basics/environment/skills/evo-jax-compute/scripts/compute_utils.py
- Executable scriptline 1
Executable file
tasks-evolved/jax-computing-basics/environment/skills/evo-jax-computing-basics/scripts/compute_utils.py
- Executable scriptline 1
Executable file
tasks-evolved/jax-computing-basics/environment/skills/evo-jax-computing-basics/scripts/io_utils.py
- Executable scriptline 1
Executable file
tasks-evolved/jax-computing-basics/environment/skills/evo-jax-computing-basics/scripts/solve_tasks.py
- Executable scriptline 1
Executable file
tasks-evolved/jax-computing-basics/environment/skills/evo-jax-io/scripts/__init__.py
- Executable scriptline 1
Executable file
tasks-evolved/jax-computing-basics/environment/skills/evo-jax-io/scripts/io_utils.py
- Executable scriptline 1
Executable file
tasks-evolved/jpg-ocr-stat/environment/skills/evo-ocr-preprocess-extract/scripts/utils.py
- Executable scriptline 1
Executable file
tasks-evolved/jpg-ocr-stat/environment/skills/evo-receipt-parse-export/scripts/utils.py
- Executable scriptline 1
Executable file
tasks-evolved/lab-unit-harmonization/environment/skills/evo-clinical-data-cleaning/scripts/utils.py
- Executable scriptline 1
Executable file
tasks-evolved/lab-unit-harmonization/environment/skills/evo-clinical-unit-harmonization/scripts/utils.py
- Executable scriptline 1
Executable file
tasks-evolved/lake-warming-attribution/environment/skills/evo-lake-data-pipeline/scripts/utils.py
- Executable scriptline 1
Executable file
tasks-evolved/lake-warming-attribution/environment/skills/evo-lake-factor-attribution/scripts/utils.py
- Executable scriptline 1
Executable file
tasks-evolved/lake-warming-attribution/environment/skills/evo-lake-trend-analysis/scripts/utils.py
- Executable scriptline 1
Executable file
tasks-evolved/latex-formula-extraction/environment/skills/evo-latex-formula-extraction/scripts/utils.py
- Executable scriptline 1
Executable file
tasks-evolved/latex-formula-extraction/environment/skills/evo-latex-syntax-validation/scripts/utils.py
- Executable scriptline 1
Executable file
tasks-evolved/latex-formula-extraction/environment/skills/evo-pdf-to-markdown/scripts/utils.py
- Executable scriptline 1
Executable file
tasks-evolved/lean4-proof/environment/skills/evo-lean4-recursive-sequence-inequality-proof/scripts/utils.py
- Executable scriptline 1
Executable file
tasks-evolved/manufacturing-codebook-normalization/environment/skills/evo-defect-pipeline/scripts/utils.py
- Executable scriptline 1
Executable file
tasks-evolved/manufacturing-codebook-normalization/environment/skills/evo-fuzzy-match/scripts/utils.py
- Executable scriptline 1
Executable file
tasks-evolved/manufacturing-codebook-normalization/environment/skills/evo-text-normalize/scripts/utils.py
- Executable scriptline 1
Executable file
tasks-evolved/manufacturing-equipment-maintenance/environment/skills/evo-reflow-handbook-parser/scripts/utils.py
- Executable scriptline 1
Executable file
tasks-evolved/manufacturing-equipment-maintenance/environment/skills/evo-reflow-json-output/scripts/utils.py
- Executable scriptline 1
Executable file
tasks-evolved/manufacturing-equipment-maintenance/environment/skills/evo-reflow-thermal-analysis/scripts/utils.py
- Executable scriptline 1
Executable file
tasks-evolved/manufacturing-fjsp-optimization/environment/skills/evo-fjsp-data-io/scripts/utils.py
- Executable scriptline 1
Executable file
tasks-evolved/manufacturing-fjsp-optimization/environment/skills/evo-fjsp-scheduler/scripts/utils.py
- Executable scriptline 1
Executable file
tasks-evolved/manufacturing-fjsp-optimization/environment/skills/evo-fjsp-validator/scripts/utils.py
- Executable scriptline 1
Executable file
tasks-evolved/mario-coin-counting/environment/skills/evo-template-matching-counter/scripts/counter_utils.py
- Executable scriptline 1
Executable file
tasks-evolved/mario-coin-counting/environment/skills/evo-video-keyframe-extraction/scripts/video_utils.py
- Executable scriptline 1
Executable file
tasks-evolved/mars-clouds-clustering/environment/skills/evo-mars-clustering-eval/scripts/utils.py
- Executable scriptline 1
Executable file
tasks-evolved/mars-clouds-clustering/environment/skills/evo-mars-grid-search/scripts/utils.py
- Executable scriptline 1
Executable file
tasks-evolved/mars-clouds-clustering/environment/skills/evo-mars-pareto-output/scripts/utils.py
- Executable scriptline 1
Executable file
tasks-evolved/multilingual-video-dubbing/environment/skills/evo-dubbing-audio-processing/scripts/utils.py
- Executable scriptline 1
Executable file
tasks-evolved/multilingual-video-dubbing/environment/skills/evo-dubbing-mux-report/scripts/utils.py
- Executable scriptline 1
Executable file
tasks-evolved/multilingual-video-dubbing/environment/skills/evo-dubbing-tts-synthesis/scripts/utils.py
- Executable scriptline 1
Executable file
tasks-evolved/offer-letter-generator/environment/skills/evo-docx-template-filler/scripts/utils.py
- Executable scriptline 1
Executable file - Network accessline 51
try: nsmap = {'w': 'http://schemas.openxmlformats.org/wordprocessingml/2006/main', - Network accessline 52
nsmap = {'w': 'http://schemas.openxmlformats.org/wordprocessingml/2006/main', - Network accessline 53
'wps': 'http://schemas.microsoft.com/office/word/2010/wordprocessingShape'} - Network accessline 125
if parent.tag.endswith('}tc') or parent.tag == 'tc': ns = '{http://schemas.openxmlformats.org/wordprocessingml/2006/main}' - Network accessline 126
ns = '{http://schemas.openxmlformats.org/wordprocessingml/2006/main}'
tasks-evolved/organize-messy-files/environment/skills/evo-document-classify-and-sort/scripts/utils.py
- Executable scriptline 1
Executable file
tasks-evolved/organize-messy-files/environment/skills/evo-document-text-extraction/scripts/utils.py
- Executable scriptline 1
Executable file - Network accessline 53
def extract_text_docx(filepath): NS = '{http://schemas.openxmlformats.org/wordprocessingml/2006/main}' - Network accessline 54
NS = '{http://schemas.openxmlformats.org/wordprocessingml/2006/main}' - Network accessline 66
def extract_text_pptx(filepath): NS = '{http://schemas.openxmlformats.org/drawingml/2006/main}' - Network accessline 67
NS = '{http://schemas.openxmlformats.org/drawingml/2006/main}'
tasks-evolved/paper-anonymizer/environment/skills/evo-pdf-content-extraction/scripts/extraction.py
- Executable scriptline 1
Executable file
tasks-evolved/paper-anonymizer/environment/skills/evo-pdf-redaction-engine/scripts/redaction.py
- Executable scriptline 1
Executable file
tasks-evolved/parallel-tfidf-search/environment/skills/evo-parallel-batch-search/scripts/utils.py
- Executable scriptline 1
Executable file
tasks-evolved/parallel-tfidf-search/environment/skills/evo-parallel-determinism/scripts/utils.py
- Executable scriptline 1
Executable file
tasks-evolved/parallel-tfidf-search/environment/skills/evo-parallel-index-building/scripts/utils.py
- Executable scriptline 1
Executable file
tasks-evolved/pddl-tpp-planning/environment/skills/evo-tpp-solver/scripts/__init__.py
- Executable scriptline 1
Executable file
tasks-evolved/pddl-tpp-planning/environment/skills/evo-tpp-solver/scripts/solve.py
- Executable scriptline 1
#!/usr/bin/env python3
tasks-evolved/pdf-excel-diff/environment/skills/evo-dataframe-diff-report/scripts/utils.py
- Executable scriptline 1
Executable file
tasks-evolved/pdf-excel-diff/environment/skills/evo-pdf-excel-extraction/scripts/utils.py
- Executable scriptline 1
Executable file
tasks-evolved/pedestrian-traffic-counting/environment/skills/evo-pedestrian-vlm-counting/SKILL.md
tasks-evolved/pedestrian-traffic-counting/environment/skills/evo-pedestrian-vlm-counting/scripts/pedestrian_counting.py
- Executable scriptline 1
Executable file - Access to secretsline 94
[Credential-related source omitted] - Access to secretsline 100
[Credential-related source omitted] - Access to secretsline 110
[Credential-related source omitted] - Access to secretsline 111
[Credential-related source omitted] - Access to secretsline 143
[Credential-related source omitted] - Access to secretsline 151
[Credential-related source omitted] - Access to secretsline 163
[Credential-related source omitted] - Access to secretsline 164
[Credential-related source omitted] - Possible obfuscationline 173
img_bytes = base64.b64decode(b64)
tasks-evolved/pedestrian-traffic-counting/environment/skills/evo-video-frame-extraction/scripts/__init__.py
- Executable scriptline 1
Executable file
tasks-evolved/pedestrian-traffic-counting/environment/skills/evo-video-frame-extraction/scripts/frame_extraction.py
- Executable scriptline 1
Executable file
tasks-evolved/pg-essay-to-audiobook/environment/skills/evo-tts-audiobook-synth/scripts/utils.py
tasks-evolved/pg-essay-to-audiobook/environment/skills/evo-web-essay-scraper/SKILL.md
- Network accessline 16
## Essay URLs - "Do Things that Don't Scale": `http://www.paulgraham.com/ds.html` - Network accessline 17
- "Do Things that Don't Scale": `http://www.paulgraham.com/ds.html` - Network accessline 18
- "Founder Mode": `http://www.paulgraham.com/foundermode.html` - Network accessline 26
text = scrape_pg_essay('http://www.paulgraham.com/ds.html')
tasks-evolved/pg-essay-to-audiobook/environment/skills/evo-web-essay-scraper/scripts/utils.py
- Executable scriptline 1
Executable file - Network accessline 9
'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/120.0.0.0 Safari/537.36' } response = requests.get(url, headers=headers, timeout=15) - Network accessline 10
} response = requests.get(url, headers=headers, timeout=15) response.raise_for_status() - Network accessline 11
response = requests.get(url, headers=headers, timeout=15)
tasks-evolved/powerlifting-coef-calc/environment/skills/evo-openpyxl-sheet-processor/scripts/utils.py
- Executable scriptline 1
Executable file
tasks-evolved/powerlifting-coef-calc/environment/skills/evo-powerlifting-dots-formula/scripts/utils.py
- Executable scriptline 1
Executable file
tasks-evolved/pptx-reference-formatting/environment/skills/evo-pptx-reference-slide/scripts/utils.py
tasks-evolved/pptx-reference-formatting/environment/skills/evo-pptx-title-detect-format/scripts/utils.py
- Executable scriptline 1
Executable file
tasks-evolved/pptx-reference-formatting/environment/skills/evo-pptx-xml-io/scripts/utils.py
- Executable scriptline 1
Executable file - Network accessline 34
return { 'a': 'http://schemas.openxmlformats.org/drawingml/2006/main', - Network accessline 35
'a': 'http://schemas.openxmlformats.org/drawingml/2006/main', - Network accessline 36
'p': 'http://schemas.openxmlformats.org/presentationml/2006/main', - Network accessline 37
'r': 'http://schemas.openxmlformats.org/officeDocument/2006/relationships',
tasks-evolved/protein-expression-analysis/environment/skills/evo-protein-expression-analysis/scripts/utils.py
- Executable scriptline 1
Executable file
tasks-evolved/protein-expression-analysis/environment/skills/evo-proteomics-excel-formulas/scripts/utils.py
- Executable scriptline 1
Executable file - Network accessline 66
ns = 'http://schemas.openxmlformats.org/spreadsheetml/2006/main' - Network accessline 120
ET.register_namespace('', ns) for p, u in [('r', 'http://schemas.openxmlformats.org/officeDocument/2006/relationships'), - Network accessline 121
for p, u in [('r', 'http://schemas.openxmlformats.org/officeDocument/2006/relationships'), - Network accessline 122
('mc', 'http://schemas.openxmlformats.org/markup-compatibility/2006'), - Network accessline 123
('x14ac', 'http://schemas.microsoft.com/office/spreadsheetml/2009/9/ac')]: - Network accessline 131
wb_root = ET.fromstring(allfiles['xl/workbook.xml']) rns = 'http://schemas.openxmlformats.org/officeDocument/2006/relationships' - Network accessline 132
rns = 'http://schemas.openxmlformats.org/officeDocument/2006/relationships' - Network accessline 139
pns = 'http://schemas.openxmlformats.org/package/2006/relationships'
tasks-evolved/python-scala-translation/environment/skills/evo-scala-idiom-mapping/scripts/idiom_mapper.py
- Executable scriptline 1
Executable file
tasks-evolved/python-scala-translation/environment/skills/evo-scala-tokenizer-generator/scripts/generate.py
- Executable scriptline 1
Executable file
tasks-evolved/quantum-numerical-simulation/environment/skills/evo-dicke-model-simulation/scripts/utils.py
- Executable scriptline 1
Executable file
tasks-evolved/quantum-numerical-simulation/environment/skills/evo-wigner-csv-export/scripts/utils.py
- Executable scriptline 1
Executable file
tasks-evolved/r2r-mpc-control/environment/skills/evo-r2r-linearization/scripts/utils.py
- Executable scriptline 1
Executable file
tasks-evolved/r2r-mpc-control/environment/skills/evo-r2r-mpc-controller/scripts/utils.py
- Executable scriptline 1
Executable file
tasks-evolved/react-performance-debugging/environment/skills/evo-nextjs-api-optimization/scripts/utils.py
- Executable scriptline 1
Executable file
tasks-evolved/react-performance-debugging/environment/skills/evo-nextjs-bundle-reduction/scripts/utils.py
- Executable scriptline 1
Executable file
tasks-evolved/react-performance-debugging/environment/skills/evo-nextjs-render-optimization/scripts/utils.py
- Executable scriptline 1
Executable file
tasks-evolved/reserves-at-risk-calc/environment/skills/evo-excel-data-extraction/scripts/utils.py
- Executable scriptline 1
Executable file
tasks-evolved/reserves-at-risk-calc/environment/skills/evo-excel-financial-formulas/scripts/utils.py
- Executable scriptline 1
Executable file
tasks-evolved/sales-pivot-analysis/environment/skills/evo-sales-pivot-analysis/scripts/run_pipeline.py
- Executable scriptline 1
#!/usr/bin/env python3
tasks-evolved/sec-financial-report/environment/skills/evo-sec13f-analyzer/scripts/utils.py
- Executable scriptline 1
Executable file
tasks-evolved/seismic-phase-picking/environment/skills/evo-seismic-data-preprocessing/scripts/utils.py
- Executable scriptline 1
Executable file
tasks-evolved/seismic-phase-picking/environment/skills/evo-seismic-phase-picking/scripts/utils.py
- Executable scriptline 1
Executable file
tasks-evolved/setup-fuzzing-py/environment/skills/evo-atheris-fuzz-driver/scripts/fuzz_driver.py
- Executable scriptline 1
Executable file
tasks-evolved/setup-fuzzing-py/environment/skills/evo-fuzz-env-runner/scripts/runner.py
- Executable scriptline 1
Executable file
tasks-evolved/setup-fuzzing-py/environment/skills/evo-python-library-discovery/scripts/discover.py
- Executable scriptline 1
Executable file
tasks-evolved/shock-analysis-demand/environment/skills/evo-macro-demand-shock-scenarios/scripts/utils.py
- Executable scriptline 1
Executable file - Network accessline 83
os.makedirs(md, exist_ok=True) with open(os.path.join(md, 'Module1.xba'), 'w') as f: f.write('<?xml version="1.0" encoding="UTF-8"?>\n<script:module xmlns:script="http://openoffice.org/2000/script" script:name="Module1" script:l - Network accessline 84
with open(os.path.join(md, 'Module1.xba'), 'w') as f: f.write('<?xml version="1.0" encoding="UTF-8"?>\n<script:module xmlns:script="http://openoffice.org/2000/script" script:name="Module1" script:language="StarBasic">\nSub RecalcAnd - Network accessline 85
f.write('<?xml version="1.0" encoding="UTF-8"?>\n<script:module xmlns:script="http://openoffice.org/2000/script" script:name="Module1" script:language="StarBasic">\nSub RecalcAndSave(sPath As String)\n Dim oDoc As Object\n Dim props(0 - Network accessline 86
with open(os.path.join(md, 'script.xlc'), 'w') as f: f.write('<?xml version="1.0" encoding="UTF-8"?>\n<library:library xmlns:library="http://openoffice.org/2000/library" library:name="Standard" library:readonly="false" library:passw - Network accessline 87
f.write('<?xml version="1.0" encoding="UTF-8"?>\n<library:library xmlns:library="http://openoffice.org/2000/library" library:name="Standard" library:readonly="false" library:passwordprotected="false">\n<library:element library:name="Module1 - Network accessline 88
with open(os.path.join(md, 'dialog.xlc'), 'w') as f: f.write('<?xml version="1.0" encoding="UTF-8"?>\n<library:library xmlns:library="http://openoffice.org/2000/library" library:name="Standard" library:readonly="false" library:passw - Network accessline 89
f.write('<?xml version="1.0" encoding="UTF-8"?>\n<library:library xmlns:library="http://openoffice.org/2000/library" library:name="Standard" library:readonly="false" library:passwordprotected="false"/>')
tasks-evolved/shock-analysis-demand/environment/skills/evo-macro-sut-import-share/scripts/utils.py
- Executable scriptline 1
Executable file
tasks-evolved/shock-analysis-demand/environment/skills/evo-macro-weo-data/scripts/utils.py
- Executable scriptline 1
Executable file
tasks-evolved/simpo-code-reproduction/environment/skills/evo-simpo-code-reproduction/scripts/run_and_save.py
- Executable scriptline 1
Executable file
tasks-evolved/simpo-code-reproduction/environment/skills/evo-simpo-code-reproduction/scripts/simpo_loss_impl.py
- Executable scriptline 1
Executable file
tasks-evolved/software-dependency-audit/environment/skills/evo-software-dependency-audit/scripts/run_audit.py
- Executable scriptline 1
#!/usr/bin/env python3
tasks-evolved/software-dependency-audit/environment/skills/evo-software-dependency-audit/scripts/utils.py
- Executable scriptline 1
Executable file
tasks-evolved/spring-boot-jakarta-migration/environment/skills/evo-spring-boot-jakarta-migration/scripts/file_utils.py
- Executable scriptline 1
Executable file
tasks-evolved/spring-boot-jakarta-migration/environment/skills/evo-spring-boot-jakarta-migration/scripts/namespace_migrator.py
- Executable scriptline 1
Executable file
tasks-evolved/spring-boot-jakarta-migration/environment/skills/evo-spring-boot-jakarta-migration/scripts/pom_migrator.py
- Executable scriptline 1
Executable file - Network accessline 169
return '''<?xml version="1.0" encoding="UTF-8"?> <project xmlns="http://maven.apache.org/POM/4.0.0" - Network accessline 170
<project xmlns="http://maven.apache.org/POM/4.0.0" - Network accessline 171
xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" - Network accessline 172
xsi:schemaLocation="http://maven.apache.org/POM/4.0.0 https://maven.apache.org/xsd/maven-4.0.0.xsd">
tasks-evolved/suricata-custom-exfil/environment/skills/evo-suricata-custom-exfil/scripts/generate_rule.py
- Executable scriptline 1
#!/usr/bin/env python3
tasks-evolved/syzkaller-ppdev-syzlang/environment/skills/evo-syzkaller-ppdev-syzlang/scripts/generate.py
- Executable scriptline 1
#!/usr/bin/env python3
tasks-evolved/taxonomy-tree-merge/environment/skills/evo-cluster-naming/scripts/name_utils.py
- Executable scriptline 1
Executable file
tasks-evolved/taxonomy-tree-merge/environment/skills/evo-semantic-hierarchical-clustering/scripts/cluster_utils.py
- Executable scriptline 1
Executable file
tasks-evolved/taxonomy-tree-merge/environment/skills/evo-taxonomy-data-pipeline/scripts/utils.py
- Executable scriptline 1
Executable file
tasks-evolved/threejs-structure-parser/environment/skills/evo-threejs-scene-parser/scripts/package.json
- Executable scriptline 1
Executable file
tasks-evolved/threejs-structure-parser/environment/skills/evo-threejs-scene-parser/scripts/parser.mjs
- Executable scriptline 1
Executable file
tasks-evolved/threejs-structure-parser/environment/skills/evo-threejs-scene-parser/scripts/run.py
- Executable scriptline 1
Executable file
tasks-evolved/threejs-to-obj/environment/skills/evo-threejs-obj-export/scripts/generate_export_script.mjs
- Executable scriptline 1
Executable file
tasks-evolved/threejs-to-obj/environment/skills/evo-threejs-obj-export/scripts/run_export.mjs
- Executable scriptline 1
Executable file
tasks-evolved/threejs-to-obj/environment/skills/evo-threejs-to-obj/scripts/convert.mjs
- Executable scriptline 1
Executable file
tasks-evolved/travel-planning/environment/skills/evo-travel-data-search/scripts/__init__.py
- Executable scriptline 1
Executable file
tasks-evolved/travel-planning/environment/skills/evo-travel-data-search/scripts/search.py
- Executable scriptline 1
Executable file
tasks-evolved/travel-planning/environment/skills/evo-travel-data-search/scripts/search_utils.py
- Executable scriptline 1
Executable file
tasks-evolved/travel-planning/environment/skills/evo-travel-data-search/scripts/utils.py
- Executable scriptline 1
Executable file
tasks-evolved/travel-planning/environment/skills/evo-travel-itinerary-builder/scripts/__init__.py
- Executable scriptline 1
Executable file
tasks-evolved/travel-planning/environment/skills/evo-travel-itinerary-builder/scripts/utils.py
- Executable scriptline 1
Executable file
tasks-evolved/travel-planning/environment/skills/evo-travel-planning/scripts/utils.py
- Executable scriptline 1
Executable file
tasks-evolved/trend-anomaly-causal-inference/environment/skills/evo-trend-anomaly-causal-inference/scripts/anomaly_detection.py
- Executable scriptline 1
Executable file
tasks-evolved/trend-anomaly-causal-inference/environment/skills/evo-trend-anomaly-causal-inference/scripts/clean_data.py
- Executable scriptline 1
Executable file
tasks-evolved/trend-anomaly-causal-inference/environment/skills/evo-trend-anomaly-causal-inference/scripts/feature_engineering.py
- Executable scriptline 1
Executable file
tasks-evolved/video-filler-word-remover/environment/skills/evo-video-filler-word-remover/scripts/utils.py
- Executable scriptline 1
Executable file
tasks-evolved/video-tutorial-indexer/environment/skills/evo-video-tutorial-indexer/scripts/chapter_detect.py
- Executable scriptline 1
Executable file
tasks-evolved/video-tutorial-indexer/environment/skills/evo-video-tutorial-indexer/scripts/transcribe.py
- Executable scriptline 1
Executable file
tasks-evolved/video-tutorial-indexer/environment/skills/evo-video-tutorial-indexer/scripts/utils.py
- Executable scriptline 1
Executable file
tasks-evolved/virtualhome-agent-planning/environment/skills/evo-pddl-plan-formatter/scripts/utils.py
- Executable scriptline 1
Executable file
tasks-evolved/virtualhome-agent-planning/environment/skills/evo-pddl-solver/scripts/utils.py
- Executable scriptline 1
Executable file
tasks-evolved/virtualhome-agent-planning/environment/skills/evo-virtualhome-agent-planning/scripts/solver.py
- Executable scriptline 1
Executable file
tasks-evolved/weighted-gdp-calc/environment/skills/evo-excel-gcc-net-exports-formulas/scripts/utils.py
- Executable scriptline 1
Executable file
tasks-evolved/weighted-gdp-calc/environment/skills/evo-excel-workbook-formula-io/scripts/utils.py
- Executable scriptline 1
Executable file - Network accessline 42
while time.time() < end: try: with socket.create_connection((host, port), timeout=1.0): - Network accessline 43
try: with socket.create_connection((host, port), timeout=1.0): return - Network accessline 44
with socket.create_connection((host, port), timeout=1.0): - Network accessline 126
src = Path(xlsx_path) ns = { 'main': 'http://schemas.openxmlformats.org/spreadsheetml/2006/main', - Network accessline 127
ns = { 'main': 'http://schemas.openxmlformats.org/spreadsheetml/2006/main', 'rel': 'http://schemas.openxmlformats.org/officeDocument/2006/relationships' - Network accessline 128
'main': 'http://schemas.openxmlformats.org/spreadsheetml/2006/main', - Network accessline 129
'rel': 'http://schemas.openxmlformats.org/officeDocument/2006/relationships' - Network accessline 135
for s in wb_xml.find('main:sheets', ns): if s.attrib.get('name') == sheet_name: sheet_rid = s.attrib.get('{http://schemas.openxmlformats.org/officeDocument/2006/relationships}id') - Network accessline 136
if s.attrib.get('name') == sheet_name: sheet_rid = s.attrib.get('{http://schemas.openxmlformats.org/officeDocument/2006/relationships}id') break - Network accessline 137
sheet_rid = s.attrib.get('{http://schemas.openxmlformats.org/officeDocument/2006/relationships}id') - Network accessline 154
v = c.find('main:v', ns) if v is None: v = ET.SubElement(c, '{http://schemas.openxmlformats.org/spreadsheetml/2006/main}v') - Network accessline 155
if v is None: v = ET.SubElement(c, '{http://schemas.openxmlformats.org/spreadsheetml/2006/main}v') v.text = repr(float(cell_value_map[ref])) - Network accessline 156
v = ET.SubElement(c, '{http://schemas.openxmlformats.org/spreadsheetml/2006/main}v') - Network accessline 165
src = Path(xlsx_path) ns = { 'main': 'http://schemas.openxmlformats.org/spreadsheetml/2006/main', - Network accessline 166
ns = { 'main': 'http://schemas.openxmlformats.org/spreadsheetml/2006/main', 'rel': 'http://schemas.openxmlformats.org/officeDocument/2006/relationships' - Network accessline 167
'main': 'http://schemas.openxmlformats.org/spreadsheetml/2006/main', - Network accessline 168
'rel': 'http://schemas.openxmlformats.org/officeDocument/2006/relationships' - Network accessline 174
for s in wb_xml.find('main:sheets', ns): if s.attrib.get('name') == sheet_name: sheet_rid = s.attrib.get('{http://schemas.openxmlformats.org/officeDocument/2006/relationships}id') - Network accessline 175
if s.attrib.get('name') == sheet_name: sheet_rid = s.attrib.get('{http://schemas.openxmlformats.org/officeDocument/2006/relationships}id') break - Network accessline 176
sheet_rid = s.attrib.get('{http://schemas.openxmlformats.org/officeDocument/2006/relationships}id') - Network accessline 193
f = c.find('main:f', ns) if f is None: f = ET.SubElement(c, '{http://schemas.openxmlformats.org/spreadsheetml/2006/main}f') - Network accessline 194
if f is None: f = ET.SubElement(c, '{http://schemas.openxmlformats.org/spreadsheetml/2006/main}f') formula = formula_text_map[ref] - Network accessline 195
f = ET.SubElement(c, '{http://schemas.openxmlformats.org/spreadsheetml/2006/main}f') - Network accessline 201
v = c.find('main:v', ns) if v is None: v = ET.SubElement(c, '{http://schemas.openxmlformats.org/spreadsheetml/2006/main}v') - Network accessline 202
if v is None: v = ET.SubElement(c, '{http://schemas.openxmlformats.org/spreadsheetml/2006/main}v') v.text = str(cell_value_map[ref]) - Network accessline 203
v = ET.SubElement(c, '{http://schemas.openxmlformats.org/spreadsheetml/2006/main}v')
tasks-evolved/xlsx-recover-data/environment/skills/evo-excel-io/scripts/excel_io.py
- Executable scriptline 1
Executable file
tasks-evolved/xlsx-recover-data/environment/skills/evo-excel-io/scripts/utils.py
- Executable scriptline 1
Executable file
tasks-evolved/xlsx-recover-data/environment/skills/evo-nasa-budget-recovery/scripts/utils.py
- Executable scriptline 1
Executable file
How the signals fit together
Facts from a static read of the files at the pinned commit. They describe what the code does, not why.
Some files could not be read; the facts below still hold.
Declared and executed: 18 facts
- Contacts api.crossref.org, which SKILL.md, the README and the plugin manifest do not mentionevo-citation-verifier/scripts/utils.py:58High confidence
- Contacts api.semanticscholar.org, which SKILL.md, the README and the plugin manifest do not mentionevo-citation-verifier/scripts/utils.py:129High confidence
- Contacts dblp.org, which SKILL.md, the README and the plugin manifest do not mentionevo-citation-verifier/scripts/utils.py:159High confidence
- Contacts d3js.org, which SKILL.md, the README and the plugin manifest do not mentionevo-web-scaffold-generator/scripts/utils.py:37High confidence
- Contacts schemas.openxmlformats.org, which SKILL.md, the README and the plugin manifest do not mentionevo-pptx-embedded-excel-updater/scripts/utils.py:46High confidence
- Contacts maven.apache.org, which SKILL.md, the README and the plugin manifest do not mentionevo-maven-build-diagnosis/scripts/utils.py:10High confidence
- Contacts www.apache.org, which SKILL.md, the README and the plugin manifest do not mentionevo-druid-cve-patch/scripts/patch_druid.py:23High confidence
- Contacts schemas.openxmlformats.org, which SKILL.md, the README and the plugin manifest do not mentionevo-docx-template-filler/scripts/utils.py:52High confidence
- Contacts schemas.microsoft.com, which SKILL.md, the README and the plugin manifest do not mentionevo-docx-template-filler/scripts/utils.py:53High confidence
- Contacts schemas.openxmlformats.org, which SKILL.md, the README and the plugin manifest do not mentionevo-document-text-extraction/scripts/utils.py:54High confidence
- Contacts schemas.openxmlformats.org, which SKILL.md, the README and the plugin manifest do not mentionevo-pptx-reference-slide/scripts/utils.py:87High confidence
- Contacts schemas.openxmlformats.org, which SKILL.md, the README and the plugin manifest do not mentionevo-pptx-xml-io/scripts/utils.py:35High confidence
- Contacts schemas.openxmlformats.org, which SKILL.md, the README and the plugin manifest do not mentionevo-proteomics-excel-formulas/scripts/utils.py:66High confidence
- Contacts schemas.microsoft.com, which SKILL.md, the README and the plugin manifest do not mentionevo-proteomics-excel-formulas/scripts/utils.py:123High confidence
- Contacts openoffice.org, which SKILL.md, the README and the plugin manifest do not mentionevo-macro-demand-shock-scenarios/scripts/utils.py:85High confidence
- Contacts maven.apache.org, which SKILL.md, the README and the plugin manifest do not mentionevo-spring-boot-jakarta-migration/scripts/pom_migrator.py:170High confidence
- Contacts www.w3.org, which SKILL.md, the README and the plugin manifest do not mentionevo-spring-boot-jakarta-migration/scripts/pom_migrator.py:171High confidence
- Contacts schemas.openxmlformats.org, which SKILL.md, the README and the plugin manifest do not mentionevo-excel-workbook-formula-io/scripts/utils.py:128High confidence
Signal confidence: 326 facts
- Executable script in prose of a file that runsevo-3d-scan-calc/scripts/utils.py:1Low confidence
- Executable script in prose of a file that runsevo-mass-report-output/scripts/utils.py:1Low confidence
- Executable script in prose of a file that runsevo-mesh-geometry-analysis/scripts/utils.py:1Low confidence
- Executable script in prose of a file that runsevo-stl-binary-parser/scripts/utils.py:1Low confidence
- Executable script in prose of a file that runsevo-adaptive-cruise-control/scripts/acc_system.py:1Low confidence
- Executable script in prose of a file that runsevo-adaptive-cruise-control/scripts/pid_controller.py:1Low confidence
- Executable script in prose of a file that runsevo-adaptive-cruise-control/scripts/simulation.py:1Low confidence
- Executable script in prose of a file that runsevo-adaptive-cruise-control/scripts/tuning.py:1Low confidence
- Executable script in prose of a file that runsevo-azure-bgp-oscillation-route-leak/scripts/utils.py:1Low confidence
- Executable script in prose of a file that runsevo-bibtex-parser/scripts/utils.py:1Low confidence
- Executable script in prose of a file that runsevo-citation-scorer/scripts/utils.py:1Low confidence
- Executable script in prose of a file that runsevo-citation-verifier/scripts/utils.py:1Low confidence
- Network access in code of a file that runsevo-citation-verifier/scripts/utils.py:19High confidence
- Network access in code of a file that runsevo-citation-verifier/scripts/utils.py:58High confidence
- Network access in code of a file that runsevo-citation-verifier/scripts/utils.py:97High confidence
- Network access in code of a file that runsevo-citation-verifier/scripts/utils.py:129High confidence
- Network access in code of a file that runsevo-citation-verifier/scripts/utils.py:159High confidence
- Executable script in code of a file that runsevo-civ6-adjacency-rules/scripts/utils.py:1High confidence
- Executable script in code of a file that runsevo-civ6-map-parser/scripts/utils.py:1High confidence
- Executable script in code of a file that runsevo-civ6-placement-optimizer/scripts/utils.py:1High confidence
- Executable script in prose of a file that runsevo-pdf-field-inspector/scripts/utils.py:1Low confidence
- Executable script in prose of a file that runsevo-pdf-form-filler/scripts/utils.py:1Low confidence
- Executable script in prose of a file that runsevo-crystallography-fraction-format/scripts/fraction_utils.py:1Low confidence
- Executable script in prose of a file that runsevo-crystallography-wyckoff-analysis/scripts/utils.py:1Low confidence
- Executable script in code of a file that runsevo-network-stats-computation/scripts/utils.py:1High confidence
- Executable script in code of a file that runsevo-pcap-feature-extraction/scripts/utils.py:1High confidence
- Executable script in code of a file that runsevo-d3v6-stock-visualization/scripts/utils.py:1High confidence
- Executable script in code of a file that runsevo-web-scaffold-generator/scripts/utils.py:1High confidence
- Network access in code of a file that runsevo-web-scaffold-generator/scripts/utils.py:35High confidence
- Network access in code of a file that runsevo-web-scaffold-generator/scripts/utils.py:36High confidence
- Network access in code of a file that runsevo-web-scaffold-generator/scripts/utils.py:37High confidence
- Executable script in prose of a file that runsevo-dialogue-dotgen/scripts/dotgen_utils.py:1Low confidence
- Executable script in code of a file that runsevo-dialogue-output/scripts/__init__.py:1High confidence
- Executable script in code of a file that runsevo-dialogue-output/scripts/utils.py:1High confidence
- Executable script in code of a file that runsevo-dialogue-parser/scripts/__init__.py:1High confidence
- Executable script in code of a file that runsevo-dialogue-parser/scripts/utils.py:1High confidence
- Executable script in code of a file that runsevo-egomotion-dynamic-analysis/scripts/utils.py:1High confidence
- Executable script in code of a file that runsevo-output-serialization/scripts/utils.py:1High confidence
- Executable script in code of a file that runsevo-video-sampling/scripts/utils.py:1High confidence
- Executable script in code of a file that runsevo-seismic-data-io/scripts/utils.py:1High confidence
- Executable script in code of a file that runsevo-seismic-phase-association/scripts/utils.py:1High confidence
- Executable script in code of a file that runsevo-seismic-phase-picking/scripts/utils.py:1High confidence
- Executable script in code of a file that runsevo-geospatial-antimeridian-plates/scripts/utils.py:1High confidence
- Executable script in code of a file that runsevo-geospatial-earthquake-distance/scripts/utils.py:1High confidence
- Executable script in prose of a file that runsevo-macro-cycle-correlation/scripts/utils.py:1Low confidence
- Executable script in prose of a file that runsevo-macro-data-ingestion/scripts/data_ingestion.py:1Low confidence
- Executable script in prose of a file that runsevo-macro-data-ingestion/scripts/utils.py:1Low confidence
- Executable script in code of a file that runsevo-acopf-network-parser/scripts/utils.py:1High confidence
- Executable script in code of a file that runsevo-acopf-report-generator/scripts/utils.py:1High confidence
- Executable script in code of a file that runsevo-acopf-solver/scripts/utils.py:1High confidence
and 276 more
Works with
| Agent | Status | Evidence | Install to |
|---|---|---|---|
| Claude Code | Native | Path .claude/skills/skill-creator/LICENSE.txt | .claude/skills/<skill-name>/ |
| Codex | Compatible | Standard SKILL.md tasks-evolved/3d-scan-calc/environment/skills/evo-3d-scan-calc/SKILL.md | .agents/skills/<skill-name>/ |
| Cursor | Compatible | Standard SKILL.md tasks-evolved/3d-scan-calc/environment/skills/evo-3d-scan-calc/SKILL.md | .cursor/skills/<skill-name>/ |
| Gemini CLI | Compatible | Standard SKILL.md tasks-evolved/3d-scan-calc/environment/skills/evo-3d-scan-calc/SKILL.md | .gemini/skills/<skill-name>/ |
| GitHub Copilot | Compatible | Standard SKILL.md tasks-evolved/3d-scan-calc/environment/skills/evo-3d-scan-calc/SKILL.md | .github/skills/<skill-name>/ |
| OpenCode | Compatible | Standard SKILL.md tasks-evolved/3d-scan-calc/environment/skills/evo-3d-scan-calc/SKILL.md | .opencode/skills/<skill-name>/ |
- Native The repository ships a manifest, folder or frontmatter field for this agent.
- Compatible A standard SKILL.md that this agent can read.
- Unknown No evidence either way.
Derived automatically from paths, manifests and frontmatter. Not tested on each agent.